> **Building with AI coding agents?** Install the authstack plugin with one command. This equips your agent with accurate Scalekit implementation patterns. > > **Recommended** (the `-y` flags skip prompts, so the command runs without an interactive terminal): > ```bash > npx -y @scalekit-inc/cli setup -y > ``` > > Global: > ```bash > npm install -g @scalekit-inc/cli > scalekit setup -y > ``` > > Supports Claude Code, Cursor, GitHub Copilot, Codex + skills for other Agent Skills-compatible agents in `~/.agents/skills`. > Skills: integrate-agentkit, implement-saaskit, add-mcp-oauth, implement-sso, implement-scim. > [Full setup guide](https://docs.scalekit.com/dev-kit/build-with-ai/) --- # Connect AI agents to the Ambiguous MCP server The Ambiguous MCP connector routes your AI agent's tool calls to Ambiguous's own MCP server through Scalekit. Each user signs in to Ambiguous once, and Scalekit stores and refreshes their tokens, so your agent never handles credentials. It comes with 1,001 tools. **Authentication:** OAuth 2.1/DCR **Categories:** Productivity, Collaboration **Tools:** 1,001: 411 read, 407 write, 183 destructive **Users sign in with:** OAuth **OAuth app:** Scalekit's or your own **Built by:** Vendor MCP **Try it:** [Playground in the Scalekit dashboard](https://app.scalekit.com/ws/signup?sk_intent=playground&provider=AMBIGUOUSMCP) ## Setup 1. ### Install the SDK **Node.js** ```bash npm install @scalekit-sdk/node dotenv ``` **Python** ```bash pip install scalekit-sdk-python python-dotenv ``` 2. ### Set your credentials Add your Scalekit credentials to your `.env` file. Find values in **[app.scalekit.com](https://app.scalekit.com)** > **Developers** > **API Credentials**. ```sh title=".env" SCALEKIT_ENVIRONMENT_URL= SCALEKIT_CLIENT_ID= SCALEKIT_CLIENT_SECRET= ``` 3. ### Create the Ambiguous MCP connection In **AgentKit > Connections**, create an Ambiguous MCP connection. The name you give it is the `connection_name` your code passes. See [Configure connections](/agentkit/connections/). Scalekit credentials are available for Ambiguous MCP server, so you don't need to register an OAuth app. 4. ### Authorize a user and make your first call **Node.js** (`quickstart.mts`) ```typescript import { ScalekitClient } from '@scalekit-sdk/node' import 'dotenv/config' import { createInterface } from 'node:readline/promises' const scalekit = new ScalekitClient( process.env.SCALEKIT_ENVIRONMENT_URL, process.env.SCALEKIT_CLIENT_ID, process.env.SCALEKIT_CLIENT_SECRET, ) const actions = scalekit.actions const connector = 'ambiguousmcp' const identifier = 'user_123' // Generate an authorization link for the user const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier }) console.log('Authorize Ambiguous MCP:', link) const rl = createInterface({ input: process.stdin, output: process.stdout }) await rl.question('Press Enter after authorizing...') rl.close() // Make your first call const result = await actions.executeTool({ connector, identifier, toolName: 'ambiguousmcp_get_billing_bonuses', toolInput: {}, }) console.log(result) ``` ```bash npx tsx quickstart.mts ``` **Python** (`quickstart.py`) ```python import os from scalekit import ScalekitClient from dotenv import load_dotenv load_dotenv() scalekit_client = ScalekitClient( env_url=os.getenv("SCALEKIT_ENVIRONMENT_URL"), client_id=os.getenv("SCALEKIT_CLIENT_ID"), client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"), ) actions = scalekit_client.actions connection_name = "ambiguousmcp" identifier = "user_123" # Generate an authorization link for the user link_response = actions.get_authorization_link( connection_name=connection_name, identifier=identifier, ) print("Authorize Ambiguous MCP:", link_response.link) input("Press Enter after authorizing...") # Make your first call result = actions.execute_tool( tool_input={}, tool_name="ambiguousmcp_get_billing_bonuses", connection_name=connection_name, identifier=identifier, ) print(result) ``` ```bash python quickstart.py ``` Each user signs in once. See [Authorize a user](/agentkit/tools/authorize/) for the full flow and statuses. ## Tools Pass the exact name to `execute_tool`, with an input like each tool's example. To ask for a tool that's missing, use the [request form](https://scalekitsupport.portal.usepylon.com/forms/request-a-connector-tool). **Node.js** ```typescript const result = await actions.executeTool({ toolName: 'ambiguousmcp_admin_integrations_list', toolInput: { request_context: '', }, connector: 'ambiguousmcp', identifier: 'user_123', }) ``` **Python** ```python result = actions.execute_tool( tool_name="ambiguousmcp_admin_integrations_list", tool_input={ "request_context": "", }, connection_name="ambiguousmcp", identifier="user_123", ) ``` `result.data` is the app's response as JSON, and `result.execution_id` (`executionId` in Node.js) is the ID of the call. ### `ambiguousmcp_admin_integrations_list` Admin integrations list · Read-only list all integrations for workspace Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_admin_integrations_slack_channels` Admin integrations slack channels · Read-only list Slack channels via bot token Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_admin_invites_list` Admin invites list · Read-only List pending, accepted, and expired workspace invites, pending first and then newest. Paginated; `pending_total` counts invites awaiting acceptance. Each row also carries `delivery` — what the provider said about the latest send of that invite email, so a bounced invite is distinguishable from an ignored one. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `limit` (`integer`, optional): Page size (default 50, max 200). - `notify` (`string`, optional): No description. - `offset` (`integer`, optional): Offset for pagination (must be >= 0). - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_admin_mail_suppressions_list` Admin mail suppressions list · Read-only list suppressed addresses Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `limit` (`integer`, optional): Page size (default 50, max 500). - `notify` (`string`, optional): No description. - `offset` (`integer`, optional): Offset for pagination (must be ≥ 0). - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). - `type` (`string`, optional): Filter by suppression type. One of: `bounce`, `complaint`. Example input: `{"request_context":""}` ### `ambiguousmcp_admin_notification_defaults_get` Admin notification defaults get · Read-only Read workspace-default email notification prefs. Returns sensible defaults (all enabled) when never configured. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_admin_usage_export` Admin usage export · Read-only Export usage stats as CSV Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_admin_usage_timeseries` Admin usage timeseries · Read-only Daily creation counts (last 14 days, split into "last 7" + "prior 7" windows) for the four hero metrics on the Overview tab. Returns `{users, documents, messages, emails}` each with `{buckets[7], total, previous_total}` so the UI can draw a sparkline + render a 7... Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_admin_user_get` Admin user get · Read-only Get one workspace user's full admin record by id. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_agent_list_connections` Agent list connections · Read-only List every live API key acting as the caller or as an agent the caller manages, classified by how it connects: `connector` (a chat app approved through OAuth), `terminal` (a terminal tool set up from a setup message) or `api_key`. An admin or owner additionally sees every agent's keys; another member's own keys never appear. `setting_up` is true while a terminal tool has not yet redeemed its setup message. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_analytics_annotations_list` Analytics annotations list · Read-only List a project's annotations, oldest date first: each is a date, an optional end date, a short text and its author, drawn on every time-series chart in the project. `from`/`to` keep only annotations overlapping that range. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `from` (`string`, optional): Only annotations that end on or after this date. - `notify` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). - `to` (`string`, optional): Only annotations that start on or before this date. Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_analytics_catalog_overrides_list` Analytics catalog overrides list · Read-only List catalog metadata overrides for the workspace. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_analytics_catalog_stats` Analytics catalog stats · Read-only Per-event last_seen_at and 30-day volume for the workspace's tracked events. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `management` (`string`, optional): Use the workspace-wide management catalog (workspace admin only), instead of a project view. One of: `true`, `false`. - `notify` (`string`, optional): No description. - `project_id` (`string`, optional): The Analytics project the read runs in. Omitted, the workspace's default project is used. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_analytics_cohorts_get` Analytics cohorts get · Read-only Read a saved cohort's name, stored criteria and member-count snapshot by ID, without recomputing its audience. Use analytics_cohorts_list to find cohort IDs. Requires a role on the report's project; `404` otherwise. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_analytics_cohorts_list` Analytics cohorts list · Read-only List saved cohort reports in the active workspace, including their definitions and stored member counts. Lists one Analytics project (`project_id`) and requires a role on it. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `project_id` (`string`, optional): The Analytics project to list. Omitted, the workspace's default project is used while clients migrate. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_analytics_dashboards_get` Analytics dashboards get · Read-only Read a saved analytics dashboard's name, stored query and tile layout by ID. Requires a role on the dashboard's project; unavailable dashboards return not found. Use analytics_dashboards_list to find accessible IDs. Requires a role on the report's project; `404` otherwise. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_analytics_dashboards_list` Analytics dashboards list · Read-only List the saved analytics dashboards of one Analytics project (`project_id`), including their tile layouts. Everyone who can view the project sees every dashboard in it. Requires a role on the report's project; `404` otherwise. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `project_id` (`string`, optional): The Analytics project to list. Omitted, the workspace's default project is used while clients migrate. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_analytics_events_get` Analytics events get · Read-only Read one Analytics evidence event owned by the caller's source workspace. Foreign and missing IDs return 404. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): The event's opaque `ev_` token, derived from its message id within its workspace. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `project_id` (`string`, optional): The Analytics project the read runs in. Omitted, the workspace's default project is used. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_analytics_events_list` Analytics events list · Read-only List source-owned Analytics evidence with bounded filters and stable pagination. Measured group IDs never grant access. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `analytics_user_id` (`string`, optional): No description. - `anonymous_id` (`string`, optional): No description. - `cursor_id` (`string`, optional): The event's opaque `ev_` token, derived from its message id within its workspace. - `cursor_timestamp` (`string`, optional): No description. - `date_from` (`string`, optional): No description. - `date_to` (`string`, optional): No description. - `event` (`string`, optional): No description. - `fields` (`string`, optional): No description. - `limit` (`integer`, optional): No description. - `notify` (`string`, optional): No description. - `project_id` (`string`, optional): The Analytics project the read runs in. Omitted, the workspace's default project is used. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). - `type` (`string`, optional): No description. One of: `track`, `identify`, `page`, `group`, `alias`. Example input: `{"request_context":""}` ### `ambiguousmcp_analytics_funnels_get` Analytics funnels get · Read-only Read a saved funnel report's name and stored conversion query definition by ID, without running the funnel. Use analytics_funnels_list to find report IDs. Requires a role on the report's project; `404` otherwise. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_analytics_funnels_list` Analytics funnels list · Read-only List saved funnel reports in the active workspace, including their names and conversion query definitions. Lists one Analytics project (`project_id`) and requires a role on it. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `project_id` (`string`, optional): The Analytics project to list. Omitted, the workspace's default project is used while clients migrate. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_analytics_insights_get` Analytics insights get · Read-only Read a saved insights report's name and stored query definition by ID, without executing the query. Use analytics_insights_list to find report IDs. Requires a role on the report's project; `404` otherwise. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_analytics_insights_list` Analytics insights list · Read-only List saved insights reports in the active workspace, including their names and query definitions. Lists one Analytics project (`project_id`) and requires a role on it. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `project_id` (`string`, optional): The Analytics project to list. Omitted, the workspace's default project is used while clients migrate. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_analytics_metric_definitions_list` Analytics metric definitions list · Read-only List metric definitions visible in the named Analytics project, or its workspace default when omitted. management=true instead reads the workspace-wide admin catalog. Each definition includes its newest stored period. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `management` (`string`, optional): Use the workspace-wide management catalog (workspace admin only), instead of a project view. One of: `true`, `false`. - `notify` (`string`, optional): No description. - `project_id` (`string`, optional): The Analytics project the read runs in. Omitted, the workspace's default project is used. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_analytics_metric_value` Analytics metric value · Read-only Read one number from a saved insight or funnel over a window: the value, the same metric over the window before it, a sparkline and a link to the report. Embedded metrics on canvas, in chips and in sheets read through this. Example: report=insights:&from=today-28d&to=now. Read only: yes. Destructive: no. Inputs: - `report` (`string`, required): The saved report to read, as `insights:` or `funnels:`. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `filters` (`string`, optional): JSON property filters composed with the saved report's filters, for dashboard number tiles. - `from` (`string`, optional): Window start (inclusive). Defaults to the report's saved window. - `notify` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). - `step` (`integer`, optional): Funnels only: report the count reaching this 1-based step instead of overall conversion. - `to` (`string`, optional): Window end (exclusive). Defaults to the report's saved window. Example input: `{"report":"","request_context":""}` ### `ambiguousmcp_analytics_projects_access_request_current` Analytics projects access request current · Read-only Return whether the caller has an open access request for the project. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_analytics_projects_get` Analytics projects get · Read-only Read one Analytics project, its view and the caller's role. `404` when the caller holds no role on it. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_analytics_projects_list` Analytics projects list · Read-only List the Analytics projects the caller holds a role on, each with its view and the caller's role. Workspace admins hold no implicit role: a private project an admin was not added to is not listed. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_analytics_projects_permissions_list` Analytics projects permissions list · Read-only List the project's members: users and teams with their roles. The Everyone team row is the workspace tier. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_analytics_query_execute` Analytics query execute · Read-only Execute an ad-hoc analytics query (events/insights/funnel/retention/cohort). Returns structured results over the project's view (the workspace default project when project_id is omitted). Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `type` (`string`, required): No description. - `aggregation` (`string`, optional): type insights only. One of: `count`, `sum`, `unique`, `ratio`. - `aggregationProperty` (`string`, optional): type insights only. - `breakdown` (`string`, optional): type insights, funnel only. - `breakdownAttribution` (`string`, optional): Which step of an attempt supplies its breakdown value: a step number (1-based, default 1), the first step with a value, or the last. A person trait key ignores it. type funnel only. - `breakdownBins` (`array`, optional): type insights only. - `conversionWindow` (`object`, optional): type funnel only. - `criteria` (`array`, optional): type cohort only. - `cursor` (`object`, optional): type events only. - `dateFrom` (`string`, optional): No description. - `dateTo` (`string`, optional): No description. - `event` (`string`, optional): type insights only. - `fields` (`string`, optional): No description. - `filters` (`string`, optional): type events, insights only. - `horizon` (`integer`, optional): type retention only. - `identityChain` (`boolean`, optional): type funnel only. - `interval` (`string`, optional): type insights, funnel, retention only. - `limit` (`integer`, optional): type events, drilldown only. - `match` (`string`, optional): type cohort only. One of: `all`, `any`. - `notify` (`string`, optional): No description. - `project_id` (`string`, optional): The Analytics project the read runs in. Omitted, the workspace's default project is used. - `ratioEvent` (`string`, optional): type insights only. - `ratioSource` (`string`, optional): type insights only. One of: `event`, `metric`. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). - `returnEvent` (`string`, optional): type retention only. - `returnFilters` (`string`, optional): No description. - `slice` (`string`, optional): type drilldown only. - `source` (`string`, optional): type insights only. One of: `event`, `metric`. - `steps` (`array`, optional): type funnel only. - `subject` (`string`, optional): type insights, funnel, retention only. One of: `person`, `group`. - `table` (`object`, optional): Returns every group as a row instead of a series, up to the table row limit; more rows answer 422 insight_table_too_large. Replaces aggregation, breakdown and interval for the read. type insights only. - `triggerEvent` (`string`, optional): type retention only. - `triggerFilters` (`string`, optional): No description. - `userIds` (`array`, optional): type insights, funnel, retention only. Example input: `{"request_context":"","type":""}` ### `ambiguousmcp_analytics_restricted_marks_list` Analytics restricted marks list · Read-only List the workspace's restricted event names, trait keys and metric keys. Workspace admin only. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_analytics_retentions_get` Analytics retentions get · Read-only Read a saved retention report's name and stored query definition by ID, without computing retention. Use analytics_retentions_list to find report IDs. Requires a role on the report's project; `404` otherwise. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_analytics_retentions_list` Analytics retentions list · Read-only List saved retention reports in the active workspace, including their names and query definitions. Lists one Analytics project (`project_id`) and requires a role on it. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `project_id` (`string`, optional): The Analytics project to list. Omitted, the workspace's default project is used while clients migrate. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_analytics_settings_get` Analytics settings get · Read-only Get the workspace's analytics settings — the timezone calendar windows such as today-7d and day/week/month buckets resolve in. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_analytics_user_timeline` Analytics user timeline · Read-only Get a user's event timeline with session grouping (30-min inactivity split). Walks the alias graph (depth 5) to include all prior identities. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `userId` (`string`, required): No description. - `date_from` (`string`, optional): Window start, inclusive (analytics window grammar). - `date_to` (`string`, optional): Window end, exclusive (analytics window grammar). - `event_type` (`string`, optional): Filter to a single event name. - `fields` (`string`, optional): No description. - `limit` (`integer`, optional): Page size (1-200, default 50). - `notify` (`string`, optional): No description. - `offset` (`integer`, optional): Page offset (default 0). - `project_id` (`string`, optional): The Analytics project the read runs in. Omitted, the workspace's default project is used. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":"","userId":""}` ### `ambiguousmcp_analytics_users_aggregates` Analytics users aggregates · Read-only List analytics user profiles from the materialized view (faster at high volume, nightly refresh). Falls back to direct read when MV is unavailable. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `limit` (`integer`, optional): Page size (1-200, default 50). - `notify` (`string`, optional): No description. - `offset` (`integer`, optional): Page offset (default 0). - `project_id` (`string`, optional): The Analytics project the read runs in. Omitted, the workspace's default project is used. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). - `search` (`string`, optional): Substring match on analytics_user_id. Example input: `{"request_context":""}` ### `ambiguousmcp_analytics_users_list` Analytics users list · Read-only List analytics user profiles (paginated, searchable). Returns traits, first_seen, last_identified. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `limit` (`integer`, optional): Page size (1-200, default 50). - `notify` (`string`, optional): No description. - `offset` (`integer`, optional): Page offset (default 0). - `project_id` (`string`, optional): The Analytics project the read runs in. Omitted, the workspace's default project is used. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). - `search` (`string`, optional): Substring match on analytics_user_id. Example input: `{"request_context":""}` ### `ambiguousmcp_analytics_write_key_list` Analytics write key list · Read-only List all writeKeys for the workspace (plaintext never returned on list). Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_asset_get_content` Asset get content · Read-only Get parent-owned image bytes for doc/sheet/deck/board/wiki/task, absent from Drive. Readable exactly by parent role/access, including external collaborators. Proxied, no redirect; Cache-Control:no-store. Active types including SVG and Canvas HTML download as attachments. With canvas_embeds off, HTML returns 404 module_unavailable; every other miss 404. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): The asset id from `/api/assets/{id}/content`. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_auth_human_sessions_list` Auth human sessions list · Read-only List the caller's own active human client sessions across workspaces, current first then last server communication descending. A session is one authentication lineage, not an inferred physical device. Excludes agent credentials, API keys, app passwords, OAuth connections and memberships. Valid legacy sessions join the inventory when first observed; renewal writers need not be enabled. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `cursor` (`string`, optional): No description. - `fields` (`string`, optional): No description. - `limit` (`integer`, optional): No description. Default: `50`. - `notify` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_auth_whoami` Auth whoami · Read-only Return the current authenticated user's profile (works with both JWT and API-key auth), including active workspace name + ID and agent kind + manager when applicable. needs_workspace_setup: true indicates the account has no workspace yet. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_batch_file_permissions` Batch file permissions · Read-only Batch-fetch permissions for up to 50 files by ID. Returns a map of file_id → permissions array. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `file_ids` (`string`, optional): Comma-separated file IDs (max 50). - `notify` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_batch_get_contacts` Batch get contacts · Read-only Fetch multiple CRM contacts by their IDs in a single request (max 100). Missing or inaccessible IDs are silently omitted from the result. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `ids` (`string`, optional): Comma-separated list of contact UUIDs (max 100). - `notify` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_batch_get_deals` Batch get deals · Read-only Fetch multiple CRM deals by their IDs in a single request (max 100). Missing or inaccessible IDs are silently omitted from the result. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `embed` (`string`, optional): Comma-separated embed fields. Supported: line_items. - `fields` (`string`, optional): No description. - `ids` (`string`, optional): Comma-separated list of deal UUIDs (max 100). - `notify` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_batch_get_files` Batch get files · Read-only Batch-fetch up to 50 files by ID. Powers drive:// embed hydration in Chat/Docs/Wiki/CRM. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `ids` (`string`, optional): Comma-separated file IDs (max 50). - `notify` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_batch_get_sheet_values` Batch get sheet values · Read-only Fetch multiple disjoint ranges from a spreadsheet in a single request. Avoids N sequential round-trips when reading KPIs from different regions. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `ranges` (`array`, required): Array of A1-style range specs. Capped at 100 per call. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","ranges":[],"request_context":""}` ### `ambiguousmcp_browse_public_channels` Browse public channels · Read-only Browse the workspace's public channels, including the ones the caller has not joined, each with a `joined` flag and member count. `list_channels` returns memberships only, so this is the only way to discover a public channel you are not in and get the id `chat_channel_join` needs. Private channels and DMs are never listed. Use this when the user asks what channels exist, or asks to join a channel by name. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `limit` (`string`, optional): Max channels to return (default 100, cap 200). - `notify` (`string`, optional): No description. - `q` (`string`, optional): Filter by a substring of the channel name or description, case-insensitive. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_bulk_export_contacts` Bulk export contacts · Read-only Export selected contacts as CSV or vCard. CSV includes core fields and custom properties; vCard preserves imported RFC 6350 properties and parameters. Read only: yes. Destructive: no. Inputs: - `ids` (`array`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `format` (`string`, optional): No description. One of: `csv`, `vcf`. Default: `csv`. - `notify` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"ids":[],"request_context":""}` ### `ambiguousmcp_bulk_export_deals` Bulk export deals · Read-only Export selected deals as CSV Read only: yes. Destructive: no. Inputs: - `ids` (`array`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"ids":[],"request_context":""}` ### `ambiguousmcp_calendar_attendee_identity` Calendar attendee identity · Read-only Resolve an attendee identifier to a current workspace member without changing the event or exposing foreign identities. Read only: yes. Destructive: no. Inputs: - `identifier` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"identifier":"","request_context":""}` ### `ambiguousmcp_calendar_conflicts` Calendar conflicts · Read-only Detect attendee scheduling conflicts. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `end` (`string`, optional): No description. - `exclude_event_id` (`string`, optional): No description. - `fields` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). - `start` (`string`, optional): No description. - `user_ids` (`string`, optional): Comma-separated user IDs. Example input: `{"request_context":""}` ### `ambiguousmcp_calendar_event_export_ics` Calendar event export ics · Read-only Export single event as .ics. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_calendar_event_reminders_list` Calendar event reminders list · Read-only List event reminders. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_calendar_export_ics` Calendar export ics · Read-only Export entire calendar as .ics. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_calendar_external_auth_url` Calendar external auth url · Read-only Start external provider OAuth. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). - `return_url` (`string`, optional): No description. Example input: `{"request_context":""}` ### `ambiguousmcp_calendar_external_calendars_list` Calendar external calendars list · Read-only List calendars on connection. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_calendar_external_connections_list` Calendar external connections list · Read-only List connected external accounts. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_calendar_resource_get` Calendar resource get · Read-only Get one bookable calendar resource by id. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_calendar_upcoming_reminders` Calendar upcoming reminders · Read-only Reminders due to fire within the next `window_hours` (default 24, max 168), soonest first. Each row carries the event it is about — title, span, status, location and calendar — so the caller renders the row without a second fetch. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `limit` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). - `window_hours` (`string`, optional): No description. Example input: `{"request_context":""}` ### `ambiguousmcp_calendars_permissions_get` Calendars permissions get · Read-only Get a single user's permission entry on a calendar, including their role, display name, and email. Useful for checking if a specific user has access without listing all permissions. Read only: yes. Destructive: no. Inputs: - `calendar_id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `user_id` (`string`, required): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"calendar_id":"","request_context":"","user_id":""}` ### `ambiguousmcp_chat_channel_engagement` Chat channel engagement · Read-only Rank the caller's channels and DMs by their own recent engagement: posts, reactions, and mentions of the caller over the last 30 days, each decaying with a 7-day half-life. Only channels the caller can view; score descending. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `limit` (`string`, optional): Max rows to return, 1 to 50 (default 50). - `notify` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_chat_channel_get` Chat channel get · Read-only Get a specific channel by UUID, with members. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_chat_channel_last_messages` Chat channel last messages · Read-only Batch-fetch the latest message preview for multiple channels in one request. Pass `ids` as a comma-separated list of channel IDs (max 100). Returns one entry per channel the caller can read, each carrying its `channel_id`. Replaces per-channel `GET /messages?limit=1` calls so a DMs/channels list renders previews without an N+1 request fan-out. Read only: yes. Destructive: no. Inputs: - `ids` (`string`, required): Comma-separated channel UUIDs (max 100) to fetch the latest message preview for. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"ids":"","request_context":""}` ### `ambiguousmcp_chat_drafts_list` Chat drafts list · Read-only The caller's chat drafts (inflight + saved), newest first. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `id` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_chat_emoji_image` Chat emoji image · Read-only Serve custom emoji image from GCS Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_chat_mentions_inbox` Chat mentions inbox · Read-only Messages from other users that @-mention the caller. Powers the Mentions tab. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `limit` (`string`, optional): Max messages to return (default 50, cap 100). - `notify` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_chat_message_send_receipt` Chat message send receipt · Read-only Read identity-only evidence for your retained keyed message in the current workspace. Requires Chat read and current channel membership. Live and spent both confirm an accepted retained row; spent returns no deleted content. Neither certifies delivery. A missing, purged, foreign, or inaccessible result is the same generic 404/unknown, never proof that sending did not occur and never permission to resend or replace the key. This Read posts nothing and creates no membership. Read only: yes. Destructive: no. Inputs: - `key` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"key":"","request_context":""}` ### `ambiguousmcp_chat_preferences` Chat preferences · Read-only Workspace-level chat preferences readable by any authenticated member (default_reactions). Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_chat_reactions_inbox` Chat reactions inbox · Read-only Messages authored by the caller that carry reactions from other users. Powers the Mentions & Reactions inbox. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `limit` (`string`, optional): Max messages to return (default 50, cap 100). - `notify` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_chat_saved_ids_list` Chat saved ids list · Read-only Get saved message IDs for a channel (for UI bookmarked state) Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_chat_sidebar_list_sections` Chat sidebar list sections · Read-only The caller's custom chat-sidebar sections, ordered by position. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_chat_thread_activity_list` Chat thread activity list · Read-only List thread-activity inbox for the current user. Powers the sidebar "Threads" inbox entry. Returns readable threads the user participates in or explicitly marked unread, with peer-only unread counts and own-inclusive unread anchors. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `limit` (`string`, optional): Max threads to return (default 30, cap 100). - `notify` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_chat_thread_get` Chat thread get · Read-only Get the replies in a chat message's thread. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `msgId` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","msgId":"","request_context":""}` ### `ambiguousmcp_check_availability` Check availability · Read-only Check free/busy availability for one or more users in a given time range. Returns busy time slots (not event details) for each user. Use this when the user asks to find a free time, check if someone is available, or schedule a meeting. Call this before create_event to avoid scheduling conflicts. Read only: yes. Destructive: no. Inputs: - `end` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `start` (`string`, required): No description. - `user_ids` (`string`, required): Comma-separated user IDs. - `fields` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"end":"","request_context":"","start":"","user_ids":""}` ### `ambiguousmcp_check_resource_availability` Check resource availability · Read-only Check if a specific resource (room, equipment) is free in a time range. Call before booking to avoid conflicts. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `resource_id` (`string`, required): No description. - `end` (`string`, optional): No description. - `fields` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). - `start` (`string`, optional): No description. Example input: `{"request_context":"","resource_id":""}` ### `ambiguousmcp_check_workspace_slug` Check workspace slug · Read-only Check whether a workspace slug is available. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). - `slug` (`string`, optional): No description. Example input: `{"request_context":""}` ### `ambiguousmcp_code_connections_list` Code connections list · Read-only List repositories offered by the workspace GitHub installation. Workspace administrators only. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_code_pull_changes_since_review` Code pull changes since review · Read-only Compare the caller's last reviewed head with the current head. Historical or truncated source is explicitly reported. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_code_pull_commit` Code pull commit · Read-only Read the diff for one commit in this pull request. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `sha` (`string`, required): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":"","sha":""}` ### `ambiguousmcp_code_pull_export` Code pull export · Read-only Export the complete review record with original anchors and attribution as versioned JSON or Markdown. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `format` (`string`, optional): No description. One of: `json`, `markdown`. Default: `json`. - `notify` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_code_pull_get` Code pull get · Read-only Read a native review, its revision, discussion, checks and merge blockers. The response carries every file patch, thread and activity entry. Pass `fields` to return only what you need, for example `id,version,blockers,data(autoMerge,mergeIntent,syncError,provider(state,headSha,baseSha,baseRef,mergeable,checks))`. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_code_pulls_list` Code pulls list · Read-only Permission-filtered pull request inbox, newest update first. Each item is a summary of what an inbox row shows; read one pull request with code_pull_get for its files, commits, description, comment bodies and activity. Pass the returned nextCursor as cursor for the next page; nextCursor is null after the last page. A page may hold fewer than limit items while nextCursor is not null. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `cursor` (`string`, optional): No description. - `fields` (`string`, optional): No description. - `limit` (`integer`, optional): No description. - `notify` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). - `repositoryId` (`string`, optional): No description. - `state` (`string`, optional): No description. One of: `open`, `closed`, `merged`, `all`. - `view` (`string`, optional): No description. One of: `all`, `needs_review`, `mine`, `following`, `assigned`, `involves`. Example input: `{"request_context":""}` ### `ambiguousmcp_code_repositories_list` Code repositories list · Read-only List repositories the caller can read, with their Code role. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_code_repository_compare` Code repository compare · Read-only Compare two repository refs before opening a pull request. Read only: yes. Destructive: no. Inputs: - `base` (`string`, required): No description. - `head` (`string`, required): No description. - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"base":"","head":"","id":"","request_context":""}` ### `ambiguousmcp_code_repository_grants` Code repository grants · Read-only Read repository access grants. Repository owner only. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_code_repository_metadata` Code repository metadata · Read-only Read the repository labels and milestones available for pull requests. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_code_repository_principals` Code repository principals · Read-only List workspace users and teams available for an explicit repository grant. Repository owner only. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_code_repository_reviewers` Code repository reviewers · Read-only List currently eligible Ambiguous reviewers, including agents. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `participants` (`string`, optional): No description. One of: `all`. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_compute_pivot_table` Compute pivot table · Read-only Compute the result of a persisted pivot table — applies row/column grouping, value aggregation, sort orders, and any matching slicer filters, and returns the rendered cells. The pivot config itself (row/column/value fields, source range) is not modified. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `pivot_id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","pivot_id":"","request_context":""}` ### `ambiguousmcp_compute_wiki_rollups` Compute wiki rollups · Read-only Compute and return rollup values for all rows in the database. Each rollup aggregates a property across related rows. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_coworkers_conversation_get` Coworkers conversation get · Read-only Proxy (workspace-isolated): get a single conversation thread. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `threadId` (`string`, required): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":"","threadId":""}` ### `ambiguousmcp_coworkers_conversations_list` Coworkers conversations list · Read-only Proxy (workspace-isolated): list conversations for the coworker in the active workspace. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `limit` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `offset` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_coworkers_execution_get` Coworkers execution get · Read-only Get one execution with full trace data — task row, parent/children lineage, conversation, reasoning cycles, and tool-call activities. Powers the Execution Trace debug view. Read only: yes. Destructive: no. Inputs: - `executionId` (`string`, required): No description. - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"executionId":"","id":"","request_context":""}` ### `ambiguousmcp_coworkers_executions_list` Coworkers executions list · Read-only Proxy: list coworker execution history (paginated). Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `limit` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `offset` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_coworkers_monitored_channels_list` Coworkers monitored channels list · Read-only Proxy (workspace-isolated): list channels the coworker is monitoring. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_coworkers_playbook_versions_get` Coworkers playbook versions get · Read-only Get one historical version's instructions and subtasks. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `playbookId` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `versionId` (`string`, required): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","playbookId":"","request_context":"","versionId":""}` ### `ambiguousmcp_coworkers_playbook_versions_list` Coworkers playbook versions list · Read-only List all versions of a playbook, newest first. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `playbookId` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","playbookId":"","request_context":""}` ### `ambiguousmcp_coworkers_playbooks_get` Coworkers playbooks get · Read-only Get one playbook with its current version's instructions and subtasks. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `playbookId` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","playbookId":"","request_context":""}` ### `ambiguousmcp_coworkers_playbooks_list` Coworkers playbooks list · Read-only List the coworker's playbooks (metadata + current version pointer). Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_crm_contact_files_list` Crm contact files list · Read-only List files attached to a contact Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_crm_contact_photo_get` Crm contact photo get · Read-only Serve the photo image stored for a CRM contact. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_crm_deal_activities` Crm deal activities · Read-only List activities for deal (owner-scoped) Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `limit` (`integer`, optional): No description. - `notify` (`string`, optional): No description. - `offset` (`integer`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). - `type` (`string`, optional): Activity timeline event type. Used for filtering and badges in the UI. One of: `note`, `call`, `email`, `meeting`, `task`, `chat`. Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_crm_deal_files_list` Crm deal files list · Read-only List files attached to a deal Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_crm_quote_pdf` Crm quote pdf · Read-only Export quote as PDF (or printable HTML with ?format=html) Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `format` (`string`, optional): No description. One of: `html`, `pdf`. - `notify` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_cycles_analytics` Cycles analytics · Read-only Burndown + summary analytics for the cycle. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_cycles_get` Cycles get · Read-only Get one task cycle and its dates by id. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_cycles_list` Cycles list · Read-only List cycles in the active workspace. `?status=` filters by status; `?limit=` (1–200) and `?offset=` paginate. `has_more` is set when the underlying query returned a hint of more rows. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `limit` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `offset` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). - `status` (`string`, optional): No description. One of: `planned`, `active`, `completed`, `cancelled`. Example input: `{"request_context":""}` ### `ambiguousmcp_cycles_velocity` Cycles velocity · Read-only Cross-cycle velocity (last N closed cycles). Default `limit=10`. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `limit` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_docs_list_named_ranges` Docs list named ranges · Read-only List all named ranges (template placeholders) defined on a document. Returns each range's name and its anchored node positions. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_documents_comments_list` Documents comments list · Read-only List threaded comments. Response includes per-user `unread_count` (comments by other users since the requester's last `mark-read`, not resolved). Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `around` (`string`, optional): With window: a comment or reply ID to include with the threads around it. An ID that is not on this container is ignored. - `fields` (`string`, optional): No description. - `limit` (`string`, optional): Most root threads to return, each with its replies. Defaults to and is capped at the comment page limit. - `notify` (`string`, optional): No description. - `offset` (`string`, optional): Root threads to skip (default 0). - `ranges` (`string`, optional): With window: comma-separated `offset:limit` root ranges to include, such as `15:50`. - `unread_island` (`string`, optional): With window: leave the first unread thread out unless it is already shown. Its run still counts it. One of: `false`. - `window` (`string`, optional): Read a long list as a window: both ends of the thread list, any `ranges` and `around`, the first unread thread, and a `window` describing what is hidden. limit and offset are ignored. Code pull requests return their ordinary list. One of: `true`. Example input: `{"id":""}` ### `ambiguousmcp_documents_export_job_content` Documents export job content · Read-only The finished file of a succeeded export job, as an attachment, for the requester only. download_url names this path when the storage cannot sign a URL; otherwise use the signed URL. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `jobId` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","jobId":"","request_context":""}` ### `ambiguousmcp_documents_export_job_get` Documents export job get · Read-only Read an export job started with documents_export_job_create. When status is succeeded, download_url is a short-lived signed URL for the file; read the job again for a new one. Only the requester, while still able to view the document, can read it; anyone else gets 404. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `jobId` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","jobId":"","request_context":""}` ### `ambiguousmcp_documents_shared_with_me` Documents shared with me · Read-only Documents shared with the calling account through an explicit permission grant, across every workspace and every identity the account owns. Excludes documents the account owns. Each row names the workspace that shared it and the role the grant carries. `scope=workspace` narrows discovery to resources in the authenticated current workspace without changing access. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `limit` (`integer`, optional): No description. - `notify` (`string`, optional): No description. - `offset` (`integer`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). - `scope` (`string`, optional): Account-wide by default. `workspace` lists only resources in the authenticated current workspace; grants and resource access remain unchanged. One of: `account`, `workspace`. - `type` (`string`, optional): Filter by document type. One of: `doc`, `sheet`, `slide`, `canvas`. Example input: `{"request_context":""}` ### `ambiguousmcp_documents_thumbnail` Documents thumbnail · Read-only Content-derived thumbnail for doc/sheet/slide cards. Returns SVG by default or PNG for Accept: image/png; cached privately for 60 seconds. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_documents_trash_list` Documents trash list · Read-only Find all deleted native Docs, Sheets, Slides and Canvas items owned by the caller. Returns their document IDs for documents_restore or documents_permanent_delete; optional type filters doc, sheet, slide or canvas. Uploaded Drive files and folders use list_trashed_files, which can also include materialized native-document shadow rows but is not a complete native-document trash list. An empty Drive-file trash result does not mean this document trash is empty. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `limit` (`integer`, optional): No description. - `notify` (`string`, optional): No description. - `offset` (`integer`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). - `type` (`string`, optional): Filter by document type. One of: `doc`, `sheet`, `slide`, `canvas`. Example input: `{"request_context":""}` ### `ambiguousmcp_documents_version_get` Documents version get · Read-only Get a version's metadata + serialized content snapshot. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `versionId` (`string`, required): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":"","versionId":""}` ### `ambiguousmcp_documents_versions_list` Documents versions list · Read-only List version snapshots, newest-first, cursor-paginated (default 50 per page). Walk via `next_cursor` until `has_more` is false. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `cursor` (`string`, optional): Opaque cursor from a prior `next_cursor`. - `fields` (`string`, optional): No description. - `limit` (`integer`, optional): No description. - `notify` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_drive_file_content` Drive file content · Read-only A file's bytes. A browser is redirected to a short-lived signed storage URL where signing is available and is otherwise sent the bytes; an MCP tool call always gets the bytes, refused 413 above the MCP result size limit. Pass `?download=true` for `Content-Disposition: attachment`; default is inline. Content retrieval failures can return 503/504 via raw Response because those statuses are outside the typed contract error-code enum. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `download` (`string`, optional): No description. - `fields` (`string`, optional): No description. - `notify` (`string`, optional): No description. Example input: `{"id":""}` ### `ambiguousmcp_drive_file_requests_list` Drive file requests list · Read-only List the caller's file requests for one owned Drive folder. Read only: yes. Destructive: no. Inputs: - `folderId` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `limit` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `offset` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"folderId":"","request_context":""}` ### `ambiguousmcp_drive_files_recent` Drive files recent · Read-only Recently used files for the current user — files they opened in the last 30 days (their own views, including files shared with them that they can still open) OR files they own created in the last 24 hours. Sorted newest first by their own last view, or creation for their own new files. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `limit` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `offset` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_drive_files_shared_with_me` Drive files shared with me · Read-only Files shared with the current user through a direct, team or external grant, newest share first (`sort=modified` orders by last modified instead). Each row carries `shared_at` and `shared_by`. Excludes files the user owns. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `limit` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `offset` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). - `sort` (`string`, optional): `shared` (default): most recently shared with you first. `modified`: most recently modified first. One of: `shared`, `modified`. Example input: `{"request_context":""}` ### `ambiguousmcp_drive_files_starred` Drive files starred · Read-only Files the current user has starred. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `limit` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `offset` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_drive_files_suggested` Drive files suggested · Read-only Files the current user is likely to want next, each with the reason it is suggested: they opened it (`opened`), someone shared it with them (`shared`), or someone else added it to a folder they own or an agent they manage created it (`added`). Covers the last 14 days, newest reason first, at most one entry per file and only files the caller can still open. Stars never influence it. Use this for the My Drive home, not for a full history; use `drive_files_recent` for everything the user opened. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `limit` (`string`, optional): How many to return, 1 to 10. Defaults to 3. - `notify` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_drive_folder_ancestors` Drive folder ancestors · Read-only Breadcrumb chain (root → leaf) for a folder. Powers breadcrumb hydration on deep-link reloads. Viewer permission is sufficient. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_drive_tag_files_list` Drive tag files list · Read-only List everything you tagged with the given tag: Drive files, docs/sheets/slides and forms you own, newest first. Docs and forms carry `document_type`. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `limit` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `offset` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_drive_tags_list` Drive tags list · Read-only Current user's tag catalog. Each tag carries name, color, and sort order. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_export_document` Export document · Read-only Export a document, sheet, or slide to one of its supported standard formats. Sheets support xlsx, csv, tsv, and ods. Returns the file bytes with Content-Type and Content-Disposition attachment headers. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `chartImages` (`array`, optional): No description. - `fields` (`string`, optional): No description. - `format` (`string`, optional): No description. - `layoutOptions` (`object`, optional): No description. - `notify` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_export_drive_file` Export drive file · Read-only Export a workspace document (Doc, Sheet, or Slide) to a file format via its Drive ID. Docs support: docx, pdf, html, md. Sheets support: xlsx, csv. Slides support: pptx, pdf, html. Binary Drive files (images, archives, etc.) cannot be exported — use download instead. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `format` (`string`, optional): Target export format (e.g., docx, pdf, xlsx, csv, pptx). Validated by the handler. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_export_form_responses` Export form responses · Read-only Download all matching form responses as CSV with field labels, display values, blank unanswered cells, and ISO submission timestamps. Streams beyond the response-list page size. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `field_id` (`string`, optional): Filter by exact value of a specific field (legacy single-filter). - `fields` (`string`, optional): No description. - `filters` (`string`, optional): URL-encoded JSON array of {field_id, op, value} objects. Operators: contains, equals, is_empty, is_not_empty. Multiple filters AND together. - `notify` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). - `submitted_after` (`string`, optional): ISO 8601 timestamp; only responses submitted after this. - `value` (`string`, optional): Required when `field_id` is set (legacy single-filter). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_export_mail_rules` Export mail rules · Read-only Download mailFilters.xml or an exact Ambiguous JSON backup. Use preview_mail_rule_export first to inspect every Gmail loss and omission. Read only: yes. Destructive: no. Inputs: - `format` (`string`, required): No description. One of: `gmail`, `ambiguous`. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). - `rule_ids` (`array`, optional): No description. Example input: `{"format":"gmail","request_context":""}` ### `ambiguousmcp_file_get_content` File get content · Read-only Read file bytes using the file sharing or its parent resource access. Parent-owned files are proxied with no-store; Drive items retain signed storage serving. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): The asset id from `/api/assets/{id}/content`. - `download` (`string`, optional): No description. One of: `true`, `false`. - `fields` (`string`, optional): No description. - `notify` (`string`, optional): No description. Example input: `{"id":""}` ### `ambiguousmcp_get_account_erasure_outcome` Get account erasure outcome · Read-only Read a deleted member's durable erasure outcome and notice-delivery state. Requires admin or owner. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_get_account_mail_client_settings` Get account mail client settings · Read-only The caller's IMAP, SMTP-submission and CalDAV settings as data — the same username, hosts and ports the `.mobileconfig` encodes, for a mail client no Apple profile covers. Hosts come from `@ambiguous/topology`, so no client carries a hostname literal. Gated exactly like the profile: 400 when the account has no Ambiguous password or no resolvable workspace address, because either makes the settings unusable. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_get_activity` Get activity · Read-only Get a single activity by ID. Useful for reading back a just-created activity via the resource URL in the activity.created event payload. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_get_billing_bonuses` Get billing bonuses · Read-only Return the workspace's full earned-bonus history, newest-first — perpetual activation bonuses merged with one-time activation grants. Powers the Home Action-bonuses card, which needs the whole history the notification feed cannot show. Any authenticated caller in the workspace. Read only: yes. Destructive: no. Inputs: none. Example input: `{}` ### `ambiguousmcp_get_billing_quota` Get billing quota · Read-only Return the workspace's unified action-meter view: plan, base/earned/topup quota, consumed-this-month, reset_at, member count + cap, trial state, active bonuses, auto-recharge config. Replaces the deprecated /api/billing/usage + /api/billing/ai-usage endpoints. Any authenticated caller in the workspace. Read only: yes. Destructive: no. Inputs: none. Example input: `{}` ### `ambiguousmcp_get_calendar` Get calendar · Read-only Get a single calendar by ID. Returns the calendar's name, color, timezone, default status, and owner. Use this when the user asks about a specific calendar's settings or before creating events to verify the timezone. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_get_calendar_colors` Get calendar colors · Read-only Get the available color palette for calendars and events. Returns 24 calendar colors and 11 event colors, each with a background and foreground hex value. Use this when the user asks what colors are available, or before setting a calendar or event color. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_get_canvas` Get canvas · Read-only Get a full canvas by id, including every element in `data.elements`. Use when you need the complete board; for a large board prefer get_canvas_manifest (ids/types/bounds only) or get_canvas_frame to stay within context budget. Coordinates: board units, top-left origin, +x right / +y down. Example: get_canvas({ id: "" }) → the board with all elements. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): Canvas board id. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_get_canvas_elements` Get canvas elements · Read-only Use to refresh changed elements: ids is comma-separated, max500; returns only requested members. An absent requested id is deleted—drop it locally. Coordinates: board units, top-left origin, +x right/+y down. Example: get_canvas_elements({id:"", ids:"el-a, el-b"}) returns only surviving elements. HTML embed markup appears as html only for one requested id; multi-id, whole-board and manifest reads omit markup. With canvas_embeds off, the single HTML read returns 404 module_unavailable; ordinary element reads omit html. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): Canvas board id. - `ids` (`string`, required): Required comma-separated element ids to fetch (max 500). Discover IDs with GET /api/canvas/{id}/manifest. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","ids":"","request_context":""}` ### `ambiguousmcp_get_canvas_frame` Get canvas frame · Read-only Get a frame (or swimlane) element and its children — every element whose `frameId` points at it. Use to read one region of a large board in full detail. Coordinates: board units, top-left origin, +x right / +y down. Example: get_canvas_frame({ id: "", frameId: "" }) → { frame, elements: [...] }. Read only: yes. Destructive: no. Inputs: - `frameId` (`string`, required): Frame (or swimlane) element id within the board. - `id` (`string`, required): Canvas board id. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"frameId":"","id":"","request_context":""}` ### `ambiguousmcp_get_canvas_manifest` Get canvas manifest · Read-only Get a bounded manifest of a board — element ids, types, and bounds only (no style/content). Use this to survey a large board cheaply, then fetch a specific frame or the full board for detail. Coordinates: board units, top-left origin, +x right / +y down. Example: get_canvas_manifest({ id: "" }) → { element_count, elements: [{ id, type, x, y, w, h }] }. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): Canvas board id. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_get_channel_messages` Get channel messages · Read-only Get recent messages from a chat channel. Returns messages with id, content (Markdown), author info, reactions, thread reply count, and timestamps. Use this when the user asks to read messages, catch up on a channel, or find a specific conversation. If the user is currently viewing a channel, use the channel ID from the page context. Messages are returned in reverse chronological order (newest first). Read only: yes. Destructive: no. Inputs: - `channel_id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `after` (`string`, optional): Message ID — return the page of messages *newer* than this message (the forward twin of `before`), oldest-of-the-page first in the same newest-first envelope. Reports `has_more_newer`. Ignored when `around` is also set. An ID outside this channel is ignored and the newest page is returned. - `around` (`string`, optional): Message ID — return a window centred on this message (roughly half the limit on each side) instead of the newest page. Takes precedence over cursor/before/before_date. An ID outside this channel is ignored and the newest page is returned. - `before` (`string`, optional): Message ID — return messages older than this message. - `before_date` (`string`, optional): ISO timestamp — return messages created before this instant. - `cursor` (`string`, optional): Opaque cursor from a prior `next_cursor`. - `fields` (`string`, optional): No description. - `limit` (`string`, optional): Max messages to return (default 50, cap 100). - `notify` (`string`, optional): No description. - `offset` (`string`, optional): Offset for legacy pagination. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). - `show_deleted` (`string`, optional): Pass 'true' to include soft-deleted messages (rendered as tombstones). One of: `true`, `false`. Example input: `{"channel_id":"","request_context":""}` ### `ambiguousmcp_get_channel_read_receipts` Get channel read receipts · Read-only Get per-member read positions for a channel — who has read up to which message. Useful for reporting on whether an announcement has been seen by everyone. Read only: yes. Destructive: no. Inputs: - `channel_id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"channel_id":"","request_context":""}` ### `ambiguousmcp_get_chat_link_previews` Get chat link previews · Read-only Get whether preview cards render under chat messages for the caller (`show_link_previews: true`, the default). The setting is the caller's own; it never changes what other people see or the sender's per-message preview size. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_get_contact` Get contact · Read-only Get a single CRM contact by ID, including full details: name, email, phone, title, company, lifecycle stage, custom properties, and timestamps. If the user is currently viewing a contact, use the contact ID from the page context. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_get_contact_score` Get contact score · Read-only Get a contact's current lead score with a breakdown of which scoring rules matched and how many points each contributed. Use this to explain why a contact is hot/cold. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_get_cover_thumbnail` Get cover thumbnail · Read-only Get the PNG thumbnail bytes for the first slide (cover image) of a presentation. Convenience endpoint — equivalent to get_slide_thumbnail with index 0. A busy renderer answers 503 slide_thumbnail_capacity_exceeded with Retry-After. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). - `size` (`string`, optional): small (200px), medium (800px, default), or large (1600px). - `v` (`string`, optional): Opaque client cache-bust version. Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_get_coworker` Get coworker · Read-only Get one AI coworker's configuration by id. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_get_coworker_status` Get coworker status · Read-only Get a coworker's runtime status (proxied from coworker service). Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_get_crm_analytics` Get crm analytics · Read-only Get analytics for accessible deals, optionally scoped to one pipeline: pipeline value by stage, conversion rates, average deal size, sales velocity, and deals breakdown. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `period` (`string`, optional): No description. One of: `this_month`, `this_quarter`, `this_year`. - `pipeline_id` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_get_crm_metrics` Get crm metrics · Read-only Get pipeline metrics summary: total open deals, total deal value, win rate, deals won/lost, and recent activity counts. Useful for high-level pipeline health questions. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `period` (`string`, optional): No description. One of: `this_month`, `this_quarter`, `this_year`. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_get_crm_reports` Get crm reports · Read-only Get CRM revenue, deals-by-source, pipeline-by-owner, and activity reports for accessible records, optionally scoped to one pipeline. Each report preserves its own timestamp axis. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `period` (`string`, optional): No description. One of: `ytd`, `this_quarter`, `this_month`, `all_time`. - `pipeline_id` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_get_current_workspace` Get current workspace · Read-only Get the active workspace (name, slug, logo). Accessible to any authenticated user. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_get_data_connector` Get data connector · Read-only Get a single data connector by ID, including its config and last-run status. Read only: yes. Destructive: no. Inputs: - `connector_id` (`string`, required): No description. - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"connector_id":"","id":"","request_context":""}` ### `ambiguousmcp_get_deal` Get deal · Read-only Get a single CRM deal by ID, including full details: title, amount, currency, stage, pipeline, contact, company, owner, probability, close date, custom properties, and timestamps. Pass embed=line_items to include the full line-items array. If the user is currently viewing a deal, use the deal ID from the page context. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `embed` (`string`, optional): Comma-separated embed fields. Supported: line_items. - `fields` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_get_deal_template` Get deal template · Read-only Get a single deal template with its line items and resolved pipeline/stage names. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_get_detailed_user_presence` Get detailed user presence · Read-only Get detailed presence for a set of users — online (≤5min), idle (5–30min), or offline — plus the lastActiveAt timestamp. Capped at 100 user IDs. Fallback/cold-hydrate surface only — the primary presence path is the full-state push over the `presence` /ws/mux channel; poll this on connect or when the socket is down, not on a steady timer. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `user_ids` (`string`, required): Comma-separated user IDs (capped at 100 per request). - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":"","user_ids":""}` ### `ambiguousmcp_get_docs_page_layout_default` Get docs page layout default · Read-only Get the caller's default layout for new Docs: `pageless_default: true` (the default) means new Docs start pageless, `false` means they start in pages. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_get_document` Get document · Read-only Get a single document by ID, including its full content and comments. If the user is currently viewing a document, use the document ID from the page context. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_get_document_footnotes` Get document footnotes · Read-only Get the footnotes from a document. Returns an array of footnotes, each with a footnoteId, body content (PM JSON), and the positions of inline references (footnoteRef nodes) in the body text. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_get_document_headers_footers` Get document headers footers · Read-only Get the default, first-page, and even-page headers and footers from a document as ProseMirror JSON nodes (or null if not set). Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_get_document_page_style` Get document page style · Read-only Get the page-level formatting for a document: margins (in PT), page size (letter/A4/legal or custom {width, height} in PT), and orientation (portrait/landscape). Empty object means default formatting. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_get_drive_storage` Get drive storage · Read-only Get Drive storage usage. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_get_drive_storage_breakdown` Get drive storage breakdown · Read-only Storage breakdown by file type. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_get_email` Get email · Read-only Get a single email by ID, including full Markdown body, sender, recipients (to/cc/bcc), subject, and timestamps. Use this when the user wants to read an email, see its contents, or reply to a specific message. If the user is currently viewing an email, use the email ID from the page context. Use detail='headers' for envelope fields only (no body), or 'minimal' for id + labels only. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `detail` (`string`, optional): Response shape: `full` (default), `headers` (envelope only), `minimal` (id + labels). One of: `full`, `headers`, `minimal`. - `fields` (`string`, optional): No description. - `mark_read` (`string`, optional): Set to false to read without marking the message read. One of: `true`, `false`. - `notify` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_get_email_attachment_url` Get email attachment url · Read-only Get an attachment download URL: signed in cloud storage, authenticated API content in local storage. Read only: yes. Destructive: no. Inputs: - `attachment_id` (`string`, required): No description. - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"attachment_id":"","id":"","request_context":""}` ### `ambiguousmcp_get_email_calendar_invite` Get email calendar invite · Read-only Get calendar invite embedded in an email. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_get_email_deliverability` Get email deliverability · Read-only Get email deliverability statistics (sent/bounced/complained/opened rates) for the past 30 days. Requires admin role. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_get_email_opens` Get email opens · Read-only Fetch open events for an email (sender only) Returns the rollup (first/last seen, open count) plus up to the most recent 50 individual open events. 403 if the caller doesn't own the email's mailbox. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_get_email_signature` Get email signature · Read-only Get the workspace default email signature (Markdown). Requires admin role. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_get_entity_preview` Get entity preview · Read-only Look up a hover-card style preview of any referenced entity (document, task, contact, deal, channel, chat message, user, event, file, wiki page, form, email). Module keys include `docs`, `tasks`, `channels`, `messages`, `users`. Returns rich details — title, status, owner, due date, amount, etc. — without fetching the full record. Use this when an entity is referenced by ID and you need a quick summary. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): Entity ID. - `module` (`string`, required): Entity module (e.g. 'document', 'task'). - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). - `wiki_context_page_id` (`string`, optional): Readable hosting Wiki page whose workspace resolves a legacy wiki://space/page address. Does not grant access to the referenced page. Example input: `{"id":"","module":"document","request_context":""}` ### `ambiguousmcp_get_event` Get event · Read-only Get a single calendar event by ID, including full details: title, description, location, start/end times, recurrence rule, status, visibility, and attendees with RSVP status. For a recurring master, occurrence_start_at selects an occurrence by its original recurrence instant, retaining a saved occurrence's own ID after rescheduling. If the user is currently viewing an event, use the event ID from the page context. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `maxAttendees` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `occurrence_start_at` (`string`, optional): Original recurrence start instant. On a recurring master, selects the saved or generated occurrence even if it moved; ordinary and saved event IDs retain their canonical row. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_get_event_instances` Get event instances · Read-only List individual occurrences of a recurring event within a date range. Expands the RRULE server-side and returns instance objects with computed start/end times. Use this to find specific occurrences (e.g., 'what meetings are on next Tuesday?') or to list upcoming instances of a series. Read only: yes. Destructive: no. Inputs: - `end` (`string`, required): End of the range, an RFC 3339 timestamp at most two years after start. - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `start` (`string`, required): Start of the range, an RFC 3339 timestamp (e.g. 2026-04-20T00:00:00Z). - `fields` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"end":"","id":"","request_context":"","start":""}` ### `ambiguousmcp_get_feedback` Get feedback · Read-only Read back one submission by its receipt. Answers only the submitter — anyone else, including other members of the submitter's workspace, gets 404. Returns the public projection: a status word (`filed` | `accepted` | `declined` | `shipped`, derived from the task Ambiguous works), the title, the priority, the task key, and timestamps. Nothing else on the task is exposed. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): The receipt returned by `POST /api/feedback`. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_get_file_info` Get file info · Read-only Get detailed information about a file or folder in Drive. Returns id, name, mime_type, size_bytes, storage_key, owner info, parent folder, and timestamps. Use this when the user asks about a specific file's details, size, type, or location. If the user is currently viewing a file in Drive, use the resource ID from page context. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_get_form` Get form · Read-only Get a form's full details including field schema, settings, publish status, and slug. Use this when the user asks about a form's fields, structure, or configuration. If the user is currently viewing a form, use the resource ID from page context. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_get_form_ab_analytics` Get form ab analytics · Read-only Get A/B test comparison analytics for a form with variants. Returns control + each variant with views, responses, completion rate, and traffic weight. Use when the user asks which variant is winning, for A/B test results, or experiment performance comparison. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_get_form_analytics` Get form analytics · Read-only Get analytics for a form: total views, total responses, completion rate, average completion time, responses-by-day (last 30 days), per-field drop-off funnel, and per-field summaries (option counts for select fields, numeric stats for rating/number fields). Use when the user asks about form performance, response rate, completion rate, or field-level statistics. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_get_form_response` Get form response · Read-only Get a single form response by ID. Returns respondent info, submitted data (keyed by field ID), and timestamp. Use when the user asks about a specific submission or wants to review a particular response. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `rid` (`string`, required): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":"","rid":""}` ### `ambiguousmcp_get_mail_approval` Get mail approval · Read-only Read one submitted email exactly as it will send — From, Reply-To, the complete To/Cc/Bcc set, subject, body with signature applied, attachment manifest, threading and requested schedule. A caller without access gets 404, never 403. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_get_mail_approval_attachment_url` Get mail approval attachment url · Read-only Presigned URL for one frozen attachment, addressed by its position in the manifest. The bytes are the copy taken at submit time, so a later edit of the source Drive file does not change what the reviewer reads. The URL is minted only after the review access check. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `index` (`integer`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","index":1,"request_context":""}` ### `ambiguousmcp_get_mail_rule` Get mail rule · Read-only Get one mail rule's conditions and actions by id. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `rule_id` (`string`, required): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":"","rule_id":""}` ### `ambiguousmcp_get_mail_rule_application` Get mail rule application · Read-only Read progress, field conflicts and the server undo_until for your own rule application. Read only: yes. Destructive: no. Inputs: - `application_id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"application_id":"","request_context":""}` ### `ambiguousmcp_get_mail_rule_changeset` Get mail rule changeset · Read-only Read your rule-management receipt, Undo deadline and reported conflicts. Read only: yes. Destructive: no. Inputs: - `changeset_id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"changeset_id":"","request_context":""}` ### `ambiguousmcp_get_mail_signature` Get mail signature · Read-only Get the effective email signature. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_get_mail_template` Get mail template · Read-only Get one saved mail template by id. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `template_id` (`string`, required): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":"","template_id":"business-pitch"}` ### `ambiguousmcp_get_mail_thread` Get mail thread · Read-only Get all emails in a thread + muted flag. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `thread_id` (`string`, required): No description. - `fields` (`string`, optional): No description. - `mailbox_id` (`string`, optional): Target a shared mailbox you hold. Omit for your own mailbox; 404 if you don't hold it. - `mark_read` (`string`, optional): Default true. Pass false for passive background revalidation without marking messages read. One of: `true`, `false`. - `notify` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":"","thread_id":""}` ### `ambiguousmcp_get_message_readers` Get message readers · Read-only List the users who have read a specific message (i.e. whose read-cursor is at or past this message). Use this to check whether a message (e.g. an important announcement) has been seen by specific people. Read only: yes. Destructive: no. Inputs: - `channel_id` (`string`, required): No description. - `message_id` (`string`, required): ID of an existing message in this channel, supplied by the user or returned by search_chat_messages/get_channel_messages. Not message text or a newly generated ID. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"channel_id":"","message_id":"","request_context":""}` ### `ambiguousmcp_get_module_availability` Get module availability · Read-only Which productivity modules are enabled for the caller's workspace: module key → boolean. Bootstrap gate for nav + routes. Read only: yes. Destructive: no. Inputs: none. Example input: `{}` ### `ambiguousmcp_get_my_access_request` Get my access request · Read-only Whether you have an open access request for a document, spreadsheet, presentation, canvas, Drive item, form, wiki page, or calendar, task, project, or CRM pipeline. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_get_notification_keywords` Get notification keywords · Read-only Get the current user's notification keywords. The user receives a mention-style notification whenever any of these words appears in a message they can read. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_get_ooo_status` Get ooo status · Read-only Check out-of-office status for one or more users. Returns per-user OOO flag and event details when applicable. Call this before scheduling to avoid inviting people who are OOO. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). - `user_ids` (`string`, optional): Comma-separated user IDs. Example input: `{"request_context":""}` ### `ambiguousmcp_get_pipeline` Get pipeline · Read-only Get a single CRM pipeline by ID with its ordered stages and its `visibility` — `workspace` when the pipeline is shared with the whole workspace, `private` when only its members reach its deals. A caller who is not a member receives 404. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_get_presentation` Get presentation · Read-only Get a presentation's full data including all slides and their elements. Returns the `SlideDeck` envelope: top-level metadata (id, title, slide_count, owner, visibility, timestamps) plus the structured deck body nested under `data` (see `SlideDeckData`). Read settings/slides/masterSlides as `response.data.slides[…]`, not at the response root. If the user is currently viewing a presentation, use the presentation ID from the page context. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_get_product` Get product · Read-only Get one CRM product from the catalog by id. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_get_project` Get project · Read-only Get a single project by ID, including task count, visibility, and metadata. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_get_quote` Get quote · Read-only Get a single CRM quote with its line items and linked deal/contact/company/owner. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_get_read_receipts_default` Get read receipts default · Read-only Get read-receipts default for new compose. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_get_resolved_presence` Get resolved presence · Read-only Cold-hydrate the resolved presence dot for a set of users in the current workspace. Returns user_id → { kind, state } — the same already-resolved dot the projector pushes over the `presence` WebSocket channel. Used on connect and as the WS-down fallback; the client renders the state and computes nothing. Capped at 100 user IDs. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `user_ids` (`string`, required): Comma-separated user IDs (capped at 100 per request). - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":"","user_ids":""}` ### `ambiguousmcp_get_scheduler_link` Get scheduler link · Read-only Get a single scheduler link (owner-scoped) with its settings and booking count. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_get_security_settings` Get security settings · Read-only Get workspace security settings (require_2fa, session_timeout_hours, password_min_length, ip_allowlist). Requires admin role. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_get_sequence` Get sequence · Read-only Get a single sequence with its full step list and current enrollment count. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_get_settings` Get settings · Read-only Get all workspace settings. Requires admin role. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_get_shared_drive` Get shared drive · Read-only Get shared drive details. Read only: yes. Destructive: no. Inputs: - `driveId` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"driveId":"","request_context":""}` ### `ambiguousmcp_get_sheet` Get sheet · Read-only Get a spreadsheet's structured data including columns, rows, and formulas. Returns the `Sheet` envelope: top-level metadata (id, title, owner, visibility, timestamps) plus the structured sheet body nested under `data` (see `SheetData`). Read the tab list as `response.data.sheets`; columns and rows are under `response.data.sheets[0]`, not at the response root. If the user is currently viewing a sheet, use the sheet ID from the page context. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_get_sheet_range` Get sheet range · Read-only Use to read a rectangular slice, max 10,000 cells. Returns 2D values and resolved start/end letters+rows; orientation=COLUMNS yields column-major inner arrays. valueRenderOption: STORED(default) preserves raw values/formula strings; FORMULA forces formulas; EVALUATED runs server engine (SUM(A1:A3)→6). Cross-tab Sheet2!A1 resolves; cross-document IMPORTRANGE returns#REF!. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `orientation` (`string`, optional): ROWS (default) or COLUMNS. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). - `spec` (`string`, optional): A1-style range — `Sheet1!A1:D10`. Required. - `valueRenderOption` (`string`, optional): STORED (default), FORMULA, or EVALUATED. Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_get_sign_audit` Get sign audit · Read-only Get the append-only audit trail for a visible signing document. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_get_sign_document` Get sign document · Read-only Get a signing document with signers and fields. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_get_slide_thumbnail` Get slide thumbnail · Read-only Get the PNG thumbnail bytes for a specific slide. Sizes: small (200px), medium (800px, default), large (1600px). A busy renderer answers 503 slide_thumbnail_capacity_exceeded with Retry-After. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `index` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). - `size` (`string`, optional): small (200px), medium (800px, default), or large (1600px). - `v` (`string`, optional): Opaque client cache-bust version. Example input: `{"id":"","index":"","request_context":""}` ### `ambiguousmcp_get_snooze_presets` Get snooze presets · Read-only Get the user's custom snooze quick-presets. Returns defaults when no custom presets are saved. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_get_swipe_actions` Get swipe actions · Read-only Get the caller's own mail-row swipe actions. Returns the defaults (right archive, left trash) when nothing is saved. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_get_task` Get task · Read-only Get a single task by ID, including full details: title, description, status, priority, assignee, due date, labels, and subtask count. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_get_task_permissions` Get task permissions · Read-only Read the caller's task editing, project-move and sharing permissions, with editable IDs for the first 200 immediate subtasks. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_get_team` Get team · Read-only Get details of a single team including its first 10 members. Returns team metadata (name, slug, visibility, join policy, email) and an embedded members list with each member's user_id, display_name, email, role, and added_at. Use this when the user asks about a specific team, its members, or 'who is in team X?'. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `team_id` (`string`, required): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":"","team_id":""}` ### `ambiguousmcp_get_undo_send_setting` Get undo send setting · Read-only Get undo-send duration preference. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_get_unread_counts` Get unread counts · Read-only Get the full unread projection (mail inbox, per-channel chat badges with mute/preference resolved, notifications, total). Used for cold-connect / reconnect hydration; live updates arrive on the mux `unread` channel. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_get_usage_stats` Get usage stats · Read-only Get workspace usage statistics including storage breakdown by user and module, active user count, API call volume, and per-module adoption metrics. Requires admin or owner role. Use this when the user asks about workspace usage, storage consumption, billing metrics, or capacity planning. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_get_user_presence` Get user presence · Read-only Get online status (true = online within the last 5 minutes) for a set of users in the current workspace. Returns user_id → boolean. Capped at 100 user IDs. Fallback/cold-hydrate surface only — the primary presence path is the full-state push over the `presence` /ws/mux channel; poll this on connect or when the socket is down, not on a steady timer. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `user_ids` (`string`, required): Comma-separated user IDs (capped at 100 per request). - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":"","user_ids":""}` ### `ambiguousmcp_get_user_status` Get user status · Read-only Get the current user's active chat status (emoji + text) and DND-until timestamp. Use this before setting or clearing the status to know the current state. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_get_users_notification_preferences` Get users notification preferences · Read-only Return the user's notification preferences, merged with defaults so newly-added keys always render. Read only: yes. Destructive: no. Inputs: none. Example input: `{}` ### `ambiguousmcp_get_vacation_settings` Get vacation settings · Read-only Get vacation auto-reply settings. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_get_wiki_database_row` Get wiki database row · Read-only Get a single database row by id. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `rowId` (`string`, required): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":"","rowId":""}` ### `ambiguousmcp_get_wiki_page` Get wiki page · Read-only Get a wiki page's full details including Markdown content, child pages, backlinks (pages that link to this page), and metadata. Use this when the user asks about a page's content, wants to read documentation, or needs to check what links to a specific page. If the user is currently viewing a wiki page, use the resource ID from page context. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_get_wiki_page_version` Get wiki page version · Read-only Get a wiki page version's full content (title + markdown body). Use this when the user asks what a previous version looked like, wants to compare versions, or needs the content of a specific snapshot. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `versionId` (`string`, required): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":"","versionId":""}` ### `ambiguousmcp_get_wiki_space_graph` Get wiki space graph · Read-only Get backlink graph data for a wiki space. Returns nodes (pages) and edges (links between pages). Use this when the user asks to visualize the knowledge graph, see how pages connect, or find highly-linked 'hub' pages. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_get_wiki_synced_block` Get wiki synced block · Read-only Get a synced block by ID. Returns the block's content and metadata. Use this when you need to read the current content of a shared block. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_get_workspace` Get workspace · Read-only Get the current workspace details (id, name, slug). Requires admin role. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_home_digest` Home digest · Read-only Workspace-home roll-up: trailing-window task velocity (with prior-window deltas) plus the actor-aggregated team digest, visibility-gated per viewer. The `window` param selects the trailing window (7d default, or 1d for Today). Accessible to any authenticated workspace member. Read only: yes. Destructive: no. Inputs: - `fields` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `window` (`string`, optional): Trailing window for the velocity counts and the digest: '7d' (default) or '1d' (Today). One of: `7d`, `1d`. Example input: `{}` ### `ambiguousmcp_list_access` List access · Read-only List named/team grants, workspace/link tiers and pending invitations for a document, spreadsheet, presentation, canvas, Drive item, form, wiki page, or calendar. id names the resource; grant IDs name recipients. To remove broad access but keep explicit collaborators and their roles, use set_visibility(visibility=restricted). The Everyone entry mirrors workspace access, not a named share. Resource kind is inferred from id. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): ID of the resource whose access is being managed, from that resource's own read or list result. A permission entry's id identifies its user or team, not the resource; supply that recipient separately as user_id or team_id. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_list_activity` List activity · Read-only List recent workspace activity (last 30 days). Scoped to the current user's workspace. Filterable by resource type, resource ID, and acting user. File activity uses current file view authority for data and totals. A file cohort above the activityFileCandidateMax platform limit returns 503 activity_scope_too_large; narrow by resource_id or user_id. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `limit` (`string`, optional): Max entries to return (capped at 100, default 50). - `notify` (`string`, optional): No description. - `offset` (`string`, optional): Pagination offset. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). - `resource_id` (`string`, optional): Filter to a specific resource (UUID). - `resource_type` (`string`, optional): Filter to a single resource type (e.g. 'document', 'task'). - `user_id` (`string`, optional): Filter to actions performed by a specific user (UUID). Example input: `{"request_context":""}` ### `ambiguousmcp_list_address_book` List address book · Read-only List the caller's address book: the shared CRM contacts they can see unioned with their own privately captured addresses, deduplicated on email with the shared record winning. Use this to resolve a recipient the user has written to before instead of asking them to retype an address. Private entries are never visible to another member. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `limit` (`integer`, optional): No description. - `notify` (`string`, optional): No description. - `q` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_list_archived_threads` List archived threads · Read-only List archived threads (one per thread) Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `cursor` (`string`, optional): Opaque cursor from a prior `next_cursor`. - `detail` (`string`, optional): Response shape: `full` (default), `headers` (envelope only), `minimal` (id + labels). One of: `full`, `headers`, `minimal`. - `fields` (`string`, optional): No description. - `label_ids` (`string`, optional): Comma-separated label names (AND semantics; case-sensitive). - `limit` (`integer`, optional): No description. - `mailbox_id` (`string`, optional): Target a shared mailbox you hold. Omit for your own mailbox; 404 if you don't hold it. - `notify` (`string`, optional): No description. - `offset` (`integer`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_list_blocked_senders` List blocked senders · Read-only List all blocked senders for current user's mailbox Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_list_calendar_events` List calendar events · Read-only List events scoped to a single calendar by its id — the RESTful path variant of list_events (`/api/calendars/events?calendar_id=…`). Requires at least viewer access to the calendar. Read only: yes. Destructive: no. Inputs: - `calendar_id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `cursor` (`string`, optional): No description. - `end` (`string`, optional): No description. - `eventTypes` (`string`, optional): No description. - `fields` (`string`, optional): No description. - `limit` (`integer`, optional): No description. - `maxAttendees` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `offset` (`integer`, optional): No description. - `orderBy` (`string`, optional): No description. - `q` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). - `showDeleted` (`string`, optional): No description. - `singleEvents` (`string`, optional): No description. - `start` (`string`, optional): No description. - `timeZone` (`string`, optional): No description. - `updatedMin` (`string`, optional): No description. Example input: `{"calendar_id":"","request_context":""}` ### `ambiguousmcp_list_calendars` List calendars · Read-only List the user's calendars. Returns calendar id, name, color, timezone, and whether it's the default. Use this to find the user's default calendar ID before creating events. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_list_channels` List channels · Read-only List the user's chat channels. Returns channels with id, name, type (public/private/dm), description, member count, and creator info. Use this when the user asks to see their channels, find a specific channel by name, or when you need a channel ID to send a message. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `include_archived` (`string`, optional): Pass '1' or 'true' to include archived channels. - `notify` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_list_charts` List charts · Read-only List every chart across every tab of the sheet. Each entry is annotated with the `tab` name it lives in. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_list_conditional_formats` List conditional formats · Read-only List all conditional formatting rules on a spreadsheet. Returns each rule's ID, ranges (A1 notation), and one canonical rule payload. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_list_contact_activities` List contact activities · Read-only List activities (notes, calls, emails, meetings, tasks) on a specific contact's timeline. Useful for summarizing recent interactions with a contact before sending an email or making a call. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `limit` (`integer`, optional): No description. - `notify` (`string`, optional): No description. - `offset` (`integer`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). - `type` (`string`, optional): Activity timeline event type. Used for filtering and badges in the UI. One of: `note`, `call`, `email`, `meeting`, `task`, `chat`. Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_list_contact_group_members` List contact group members · Read-only List all contacts that are members of a contact group. Returns the contact id, name, email, and type for each member. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_list_contact_groups` List contact groups · Read-only List all contact groups in the workspace with their member counts. Groups are named collections for organizing contacts (e.g., 'Conference leads 2026'). Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_list_contacts` List contacts · Read-only List CRM contacts. Supports filtering by type, lifecycle stage, owner, and text search. Returns contacts with id, name, email, phone, type, lifecycle_stage, company, and timestamps. Use this when the user asks to see their contacts, find a person, or list companies. Also use this with the 'q' parameter to search for existing contacts BEFORE creating new ones to prevent duplicates. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `company_id` (`string`, optional): Filter to contacts belonging to this company. - `cursor` (`string`, optional): Opaque cursor from a prior `next_cursor` for page-after-page walking. - `fields` (`string`, optional): No description. - `group_id` (`string`, optional): Filter to contacts that are members of this contact group. - `lifecycle_stage` (`string`, optional): Filter by funnel stage. - `limit` (`integer`, optional): Max rows per page (1-500, default 50). The People view requests 500 for the unified company-grouped UI. - `notify` (`string`, optional): No description. - `offset` (`integer`, optional): Offset-based pagination; use `cursor` for large result sets. - `owner_id` (`string`, optional): Filter to contacts owned by this user. - `q` (`string`, optional): Free-text search across name/email/phone. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). - `type` (`string`, optional): Filter by contact type (`person` or `company`). One of: `person`, `company`. Example input: `{"request_context":""}` ### `ambiguousmcp_list_crm_activities` List crm activities · Read-only List recent CRM activity visible to the current user across contact and deal timelines. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `limit` (`integer`, optional): No description. - `notify` (`string`, optional): No description. - `offset` (`integer`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). - `type` (`string`, optional): Activity timeline event type. Used for filtering and badges in the UI. One of: `note`, `call`, `email`, `meeting`, `task`, `chat`. Example input: `{"request_context":""}` ### `ambiguousmcp_list_crm_lifecycle_stages` List crm lifecycle stages · Read-only Read the workspace People lifecycle registry, including archived stages. An unconfigured workspace uses the seven default stages. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_list_crm_property_definitions` List crm property definitions · Read-only List the workspace's typed custom-property definitions for contacts and deals, including relation properties that link a record to another contact, company, or deal. Optionally filter by entity_type. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `entity_type` (`string`, optional): No description. One of: `contact`, `company`, `deal`. - `fields` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_list_crm_views` List crm views · Read-only List the user's saved CRM views (filter + sort presets for contacts/companies/deals). Views personalize how CRM data is displayed without changing the underlying records. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `entity_type` (`string`, optional): Which list page the saved view applies to. One of: `contacts`, `companies`, `deals`. - `fields` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_list_crm_workspace_users` List crm workspace users · Read-only List all users (humans and agents) in the current workspace who can own CRM records. Use before assigning contacts or deals to a specific owner_id. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_list_custom_emojis` List custom emojis · Read-only List all custom emojis uploaded to the current workspace. Returns each emoji with id, name (without colons), image URL, and creator info. Use this to discover what custom emojis are available before referring to them by name. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_list_data_connector_run_history` List data connector run history · Read-only List recent execution history for a data connector. Each row records one manual or scheduled run with its status, duration, row count, and error (if any). Use the `limit` query param to cap the page size (default 20, max 100). Results are ordered by completion time, newest first. Read only: yes. Destructive: no. Inputs: - `connector_id` (`string`, required): No description. - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `limit` (`string`, optional): Page size, integer 1–100 (default 20). - `notify` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"connector_id":"","id":"","request_context":""}` ### `ambiguousmcp_list_data_connectors` List data connectors · Read-only List data connectors registered on a sheet. Connectors fetch data from external sources (URL, CSV, etc.) into specific cells. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_list_deal_line_items` List deal line items · Read-only List all line items for a deal, plus the computed total. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_list_deal_templates` List deal templates · Read-only List deal templates in the workspace (reusable deal presets: default pipeline, stage, amount, probability, and line items). Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `active_only` (`boolean`, optional): Hide products where `active=false` when true. - `fields` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `q` (`string`, optional): Search by name or SKU. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_list_deals` List deals · Read-only List CRM deals. Supports filtering by pipeline, stage, and status. Returns deals with id, title, amount, currency, stage, pipeline, contact, status, and timestamps. Use this when the user asks to see their deals, check the pipeline, or find opportunities. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `company_id` (`string`, optional): No description. - `contact_id` (`string`, optional): No description. - `cursor` (`string`, optional): No description. - `embed` (`string`, optional): Comma-separated embed fields. Supported: line_items. - `fields` (`string`, optional): No description. - `limit` (`integer`, optional): No description. - `notify` (`string`, optional): No description. - `offset` (`integer`, optional): No description. - `owner_id` (`string`, optional): No description. - `pipeline_id` (`string`, optional): No description. - `q` (`string`, optional): Free-text search across deal titles. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). - `stage_id` (`string`, optional): No description. - `status` (`string`, optional): Lifecycle of a deal. `won` and `lost` close the deal; `lost` requires a `lost_reason`. One of: `open`, `won`, `lost`. Example input: `{"request_context":""}` ### `ambiguousmcp_list_documents` List documents · Read-only List the current user's documents in the authenticated current workspace. Optionally filter by type. Documents the user owns in another workspace are listed only with `scope=account`; `scope=workspace` also includes documents shared in this workspace with the user's other account identities. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `cursor` (`string`, optional): Opaque cursor from a prior `next_cursor`. - `fields` (`string`, optional): No description. - `include_filed` (`string`, optional): Pass 'true' to also list documents filed in a Drive folder or shared drive. Without it only unfiled documents are listed, which is what Drive's root view relies on. Pass 'true' whenever you want every document the user can see. One of: `true`, `false`. - `limit` (`integer`, optional): Page size. Clamped server-side to the `paginationMax` platform limit (200) — a larger value is served at the cap with `has_more` and a `next_cursor`, never rejected. - `max_results` (`integer`, optional): Alias for `limit`; clamped the same way. - `notify` (`string`, optional): No description. - `offset` (`integer`, optional): Rows to skip. Clamped server-side to the `paginationOffsetMax` platform limit; page deeper with `cursor`, which walks the whole set at constant cost. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). - `scope` (`string`, optional): Account-wide by default. `workspace` lists only resources in the authenticated current workspace; grants and resource access remain unchanged. One of: `account`, `workspace`. - `starred` (`string`, optional): Pass 'true' to return only starred documents. One of: `true`, `false`. - `type` (`string`, optional): Filter by document type. One of: `doc`, `sheet`, `slide`, `canvas`. Example input: `{"request_context":""}` ### `ambiguousmcp_list_drafts` List drafts · Read-only List the unsent draft emails in this mailbox. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `cursor` (`string`, optional): Opaque cursor from a prior `next_cursor`. - `detail` (`string`, optional): Response shape: `full` (default), `headers` (envelope only), `minimal` (id + labels). One of: `full`, `headers`, `minimal`. - `fields` (`string`, optional): No description. - `label_ids` (`string`, optional): Comma-separated label names (AND semantics; case-sensitive). - `limit` (`integer`, optional): No description. - `mailbox_id` (`string`, optional): Target a shared mailbox you hold. Omit for your own mailbox; 404 if you don't hold it. - `notify` (`string`, optional): No description. - `offset` (`integer`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_list_drive_folders` List drive folders · Read-only List only folders (not files) in Drive — useful for folder pickers. Pass root to scope the listing to My Drive, shared drives, or Shared with me. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `parent_id` (`string`, optional): No description. - `q` (`string`, optional): Name filter. Spans every root at any depth, so parent_id and root are ignored. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). - `root` (`string`, optional): Omit for the legacy merged listing; supply to scope results to one root. One of: `my_drive`, `shared_drives`, `shared_with_me`. - `shared_drive_id` (`string`, optional): Limit shared-drive folders to this drive, within the caller's workspace and membership. Example input: `{"request_context":""}` ### `ambiguousmcp_list_email_attachments` List email attachments · Read-only List attachments for an email Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_list_enrollment_events` List enrollment events · Read-only Get the event log for a single sequence enrollment (step-executed, email-opened, email-replied, branch-taken, completed). Useful for auditing why a contact moved to a particular step. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_list_event_resources` List event resources · Read-only List resources currently booked for an event (rooms, equipment). Read only: yes. Destructive: no. Inputs: - `event_id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"event_id":"","request_context":""}` ### `ambiguousmcp_list_events` List events · Read-only List calendar events across all of the user's calendars. Supports filtering by date range, calendar, and free-text search. Returns events with id, title, start/end times, location, status, and attendees. Use this when the user asks to see their schedule, upcoming meetings, or events for a date. Use the q parameter to search for events by keyword (matches title, description, location, and attendee names). Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `calendar_id` (`string`, optional): No description. - `cursor` (`string`, optional): No description. - `end` (`string`, optional): No description. - `eventTypes` (`string`, optional): No description. - `fields` (`string`, optional): No description. - `limit` (`integer`, optional): No description. - `maxAttendees` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `offset` (`integer`, optional): No description. - `orderBy` (`string`, optional): No description. - `q` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). - `showDeleted` (`string`, optional): No description. - `singleEvents` (`string`, optional): No description. - `start` (`string`, optional): No description. - `timeZone` (`string`, optional): No description. - `updatedMin` (`string`, optional): No description. Example input: `{"request_context":""}` ### `ambiguousmcp_list_feedback` List feedback · Read-only List the caller's own submissions, newest first, as public projections (see `get_feedback`). Paginated with `limit` (default 50) and `offset`. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `limit` (`string`, optional): Page size (default 50, capped at the platform pagination max). - `notify` (`string`, optional): No description. - `offset` (`string`, optional): Rows to skip (default 0). - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_list_files` List files · Read-only List files and folders in the user's Drive. Returns items with id, name, mime_type, size_bytes, is_folder, parent_folder_id, owner info, and timestamps. Use this when the user asks to see their files, browse a folder, find a specific file, or check what's in Drive. If the user is currently viewing Drive, use context for the current folder. A `parent_id` the caller cannot view answers 404, exactly as an absent folder does; a folder shared from another workspace is browsed through `GET /api/drive/{id}/children` instead. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `added_by` (`string`, optional): `agents`: only items an agent added (the item's owner is an agent identity). One of: `agents`. - `cursor` (`string`, optional): Opaque continuation token from `next_cursor`. Only returned for the default order (`modified`, newest first). - `fields` (`string`, optional): No description. - `folders_first` (`string`, optional): `true` (default) lists folders before files. `false` orders folders and files together by `sort`; keyset cursors are then not returned, so page with `offset`. One of: `true`, `false`. - `in_folder` (`string`, optional): Search only: the folder to search inside, including its subfolders. A folder the caller cannot view answers 404. - `kind` (`string`, optional): Restrict the listing to one kind of item. `documents`, `spreadsheets` and `presentations` include both workspace docs and uploaded office files of that kind; `images` and `pdf` include uploaded files only. One of: `folders`, `documents`, `spreadsheets`, `presentations`, `forms`, `images`, `pdf`. - `limit` (`string`, optional): Page size. - `location` (`string`, optional): Search only: `my_drive` is what you own outside shared drives, `shared_with_me` is what others own outside shared drives, `shared_drives` is shared-drive content. One of: `my_drive`, `shared_with_me`, `shared_drives`. - `modified_after` (`string`, optional): Only items modified at or after this instant (ISO 8601). - `notify` (`string`, optional): No description. - `offset` (`string`, optional): Number of items to skip; use with any order or filter, following `has_more`. - `order` (`string`, optional): Direction of `sort`. Defaults to `desc` for `modified`, otherwise `asc` for `name` and `owner` and `desc` for the rest. One of: `asc`, `desc`. - `owner_id` (`string`, optional): Only items owned by this user. - `parent_id` (`string`, optional): No description. - `q` (`string`, optional): Search text. When set, the listing is a search across everything the caller can open: every word must appear in an item's name, its scanned text, or a document's body. `kind`, `owner_id`, `modified_after`, `added_by`, `location` and `in_folder` filter it; results are most relevant first (more words in the name first, scanned-text matches last) unless `sort` is `modified` or `name`; `limit` (at most 50) and `offset` page it. Each result carries `location` and `search_match`. Operators such as `type:pdf` and `modified:this-week` in the text still work. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). - `section` (`string`, optional): `trash` lists trashed items instead of a folder. - `sort` (`string`, optional): Order of the listing. Folders come before files unless `folders_first=false`. Defaults to `modified`. `last_opened` uses the caller's own last view and falls back to the modified, then created, time for items they never opened. One of: `name`, `owner`, `modified`, `last_opened`, `created`, `size`. - `type` (`string`, optional): Legacy search-only kind filter: folders, documents, images, videos, audio or archives. Ignored without `q`; prefer `kind`. Example input: `{"request_context":""}` ### `ambiguousmcp_list_folder_children` List folder children · Read-only List the direct children of one folder, named in the path. Use this to browse into a folder — including one shared with you from another workspace, which the `parent_id` form of the list endpoint cannot return. Answers 404 for a folder the caller cannot view, exactly as an absent one does. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `added_by` (`string`, optional): `agents`: only items an agent added (the item's owner is an agent identity). One of: `agents`. - `cursor` (`string`, optional): Opaque continuation token from `next_cursor`. Only returned for the default order (`modified`, newest first). - `fields` (`string`, optional): No description. - `folders_first` (`string`, optional): `true` (default) lists folders before files. `false` orders folders and files together by `sort`; keyset cursors are then not returned, so page with `offset`. One of: `true`, `false`. - `kind` (`string`, optional): Restrict the listing to one kind of item. `documents`, `spreadsheets` and `presentations` include both workspace docs and uploaded office files of that kind; `images` and `pdf` include uploaded files only. One of: `folders`, `documents`, `spreadsheets`, `presentations`, `forms`, `images`, `pdf`. - `limit` (`string`, optional): Page size. - `modified_after` (`string`, optional): Only items modified at or after this instant (ISO 8601). - `notify` (`string`, optional): No description. - `offset` (`string`, optional): Number of items to skip; use with any order or filter, following `has_more`. - `order` (`string`, optional): Direction of `sort`. Defaults to `desc` for `modified`, otherwise `asc` for `name` and `owner` and `desc` for the rest. One of: `asc`, `desc`. - `owner_id` (`string`, optional): Only items owned by this user. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). - `sort` (`string`, optional): Order of the listing. Folders come before files unless `folders_first=false`. Defaults to `modified`. `last_opened` uses the caller's own last view and falls back to the modified, then created, time for items they never opened. One of: `name`, `owner`, `modified`, `last_opened`, `created`, `size`. Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_list_form_responses` List form responses · Read-only List responses submitted to a form. Returns responses with respondent info, submitted data (keyed by field ID), and timestamps. Use this when the user asks to see form results, check submissions, analyze feedback, or export response data. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `cursor` (`string`, optional): No description. - `field_id` (`string`, optional): Filter by exact value of a specific field (legacy single-filter). - `fields` (`string`, optional): No description. - `filters` (`string`, optional): URL-encoded JSON array of {field_id, op, value} objects. Operators: contains, equals, is_empty, is_not_empty. Multiple filters AND together. - `limit` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `offset` (`string`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). - `submitted_after` (`string`, optional): ISO 8601 timestamp; only responses submitted after this. - `value` (`string`, optional): Required when `field_id` is set (legacy single-filter). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_list_form_variants` List form variants · Read-only List A/B test variants for a form. Returns each variant's id, name, traffic weight, active status, and variant form ID. Use when the user asks about their A/B tests, variant list, or experiment setup. Read only: yes. Destructive: no. Inputs: - `id` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"id":"","request_context":""}` ### `ambiguousmcp_list_forms` List forms · Read-only List the user's forms. Returns forms with id, title, slug, is_published, response count, timestamps, and the caller's own star and Drive tags. Pass `starred=true` for only the forms you starred. Use this when the user asks to see their forms, find a specific form, or check form status. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `fields` (`string`, optional): No description. - `is_published` (`string`, optional): 'true' or 'false' to filter by publish state. One of: `true`, `false`. - `limit` (`string`, optional): No description. - `notify` (`string`, optional): No description. - `offset` (`string`, optional): No description. - `q` (`string`, optional): Search filter on title/description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). - `starred` (`string`, optional): 'true' to list only the forms you starred. One of: `true`, `false`. Example input: `{"request_context":""}` ### `ambiguousmcp_list_forwarding_addresses` List forwarding addresses · Read-only List forwarding addresses + recent log. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_list_identity_api_keys` List identity api keys · Read-only List the calling user's own API keys. Scoped to `c.var.user.id` — does not return keys belonging to other users in the same workspace. Admins managing other users' keys should use `GET /api/admin/api-keys`. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"request_context":""}` ### `ambiguousmcp_list_inbox` List inbox · Read-only List the user's received emails (inbox). Returns emails with id, from, subject, preview, read status, and sent timestamp. Use this when the user asks to check their inbox, see recent emails, or find a specific email. Use detail='headers' for bandwidth-efficient scanning (omits body), or 'minimal' for id + labels only. Use label_ids to filter by specific labels (AND semantics — all listed labels must be present). Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `assigned` (`string`, optional): Shared-mailbox queue only: `me` for threads you hold, `unassigned` for threads nobody holds. 400 on a personal mailbox or with a non-inbox `folder`. One of: `me`, `unassigned`. - `cursor` (`string`, optional): Opaque cursor from a prior `next_cursor`. - `detail` (`string`, optional): Response shape: `full` (default), `headers` (envelope only), `minimal` (id + labels). One of: `full`, `headers`, `minimal`. - `fields` (`string`, optional): No description. - `folder` (`string`, optional): `inbox` (default) | `sent` | `drafts` | `starred` | `snoozed` | `scheduled`. One of: `inbox`, `sent`, `drafts`, `starred`, `snoozed`, `scheduled`. - `label_ids` (`string`, optional): Comma-separated label names (AND semantics; case-sensitive). - `limit` (`integer`, optional): No description. - `mailbox_id` (`string`, optional): Target a shared mailbox you hold. Omit for your own mailbox; 404 if you don't hold it. - `notify` (`string`, optional): No description. - `offset` (`integer`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). - `threaded` (`string`, optional): Default true; pass `false` to flatten. - `unread` (`string`, optional): No description. Example input: `{"request_context":""}` ### `ambiguousmcp_list_mail_approvals` List mail approvals · Read-only List email submissions awaiting a human decision. Returns the caller's own submissions plus the ones they may decide — as the submitting agent's current manager, or as a workspace admin/owner. A former manager sees nothing. Read only: yes. Destructive: no. Inputs: - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `agent_id` (`string`, optional): Narrow to one agent's submissions: email it sent, and external email addressed to it. - `fields` (`string`, optional): No description. - `limit` (`integer`, optional): No description. - `notify` (`string`, optional): No description. - `offset` (`integer`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). - `role` (`string`, optional): Narrow to the caller's side of the queue. Omitted returns both. One of: `author`, `reviewer`. - `status` (`string`, optional): Narrow to one decision state. `pending` is the Needs approval queue. One of: `pending`, `approved`, `changes_requested`, `rejected`, `withdrawn`. Example input: `{"request_context":""}` ### `ambiguousmcp_list_mail_by_label` List mail by label · Read-only List emails with a specific label Read only: yes. Destructive: no. Inputs: - `label` (`string`, required): No description. - `request_context` (`string`, required): Explain how this request supports the user's goal: 20–30 words, third person, without we/I/you. Exclude credentials, secrets and personal information. - `cursor` (`string`, optional): Opaque cursor from a prior `next_cursor`. - `detail` (`string`, optional): Response shape: `full` (default), `headers` (envelope only), `minimal` (id + labels). One of: `full`, `headers`, `minimal`. - `fields` (`string`, optional): No description. - `label_ids` (`string`, optional): Comma-separated label names (AND semantics; case-sensitive). - `limit` (`integer`, optional): No description. - `mailbox_id` (`string`, optional): Target a shared mailbox you hold. Omit for your own mailbox; 404 if you don't hold it. - `notify` (`string`, optional): No description. - `offset` (`integer`, optional): No description. - `reference_resource_id` (`string`, optional): Optional ID of an accessible Ambiguous resource where this work was requested (email, chat, comment, task, document or file). Example input: `{"label":"