> **Building with AI coding agents?** If you're using an AI coding agent, install the official Scalekit plugin. It gives your agent full awareness of the Scalekit API — reducing hallucinations and enabling faster, more accurate code generation.
>
> - **Claude Code**: `/plugin marketplace add scalekit-inc/claude-code-authstack` then `/plugin install <auth-type>@scalekit-auth-stack`
> - **GitHub Copilot CLI**: `copilot plugin marketplace add scalekit-inc/github-copilot-authstack` then `copilot plugin install <auth-type>@scalekit-auth-stack`
> - **Codex**: run the bash installer, restart, then open Plugin Directory and enable `<auth-type>`
> - **Skills CLI** (Windsurf, Cline, 40+ agents): `npx skills add scalekit-inc/skills --list` then `--skill <skill-name>`
>
> `<auth-type>` / `<skill-name>`: `agentkit`, `full-stack-auth`, `mcp-auth`, `modular-sso`, `modular-scim` — [Full setup guide](https://docs.scalekit.com/dev-kit/build-with-ai/)

---

# Granola MCP

**Authentication:** OAuth 2.0
**Categories:** Ai, Automation, Communication
## What you can do

Connect this agent connector to let your agent:

- **Get get** — Get detailed meeting information for one or more Granola meetings by ID
- **Query query** — Query Granola about the user's meetings using natural language
- **List list** — List the user's Granola meeting notes within a time range

## Authentication

This connector uses **OAuth 2.0**. Scalekit acts as the OAuth client: it redirects your user to Granola MCP, obtains an access token, and automatically refreshes it before it expires. Your agent code never handles tokens directly — you only pass a `connectionName` and a user `identifier`.

You supply your Granola MCP **Connected App** credentials (Client ID + Secret) once per environment in the Scalekit dashboard.

## Code examples

Connect a user's Granola account and query Granola's official MCP server through Scalekit. Scalekit handles the OAuth flow, token storage, and tool execution automatically.

Granola MCP is primarily used through Scalekit tools. Use `scalekit_client.actions.execute_tool()` to search meeting notes, list meetings, fetch meeting details, and retrieve transcripts without calling the upstream MCP server directly.

## Tool Calling

Use this connector when you want an agent to work with Granola meeting content, including summaries, notes, attendees, and transcripts.

- Use `granolamcp_query_granola_meetings` for natural-language questions such as decisions, action items, or follow-ups from past meetings.
- Use `granolamcp_list_meetings` to find meetings in a time window before drilling into specific meeting IDs.
- Use `granolamcp_get_meetings` when you already know the Granola meeting IDs and need richer metadata or notes.
- Use `granolamcp_get_meeting_transcript` when exact wording matters and you need the verbatim transcript instead of summarized notes.

  ### Python

```python title="examples/granolamcp_query_meetings.py"

from scalekit.client import ScalekitClient

scalekit_client = ScalekitClient(
    client_id=os.environ["SCALEKIT_CLIENT_ID"],
    client_secret=os.environ["SCALEKIT_CLIENT_SECRET"],
    env_url=os.environ["SCALEKIT_ENV_URL"],
)

auth_link = scalekit_client.actions.get_authorization_link(
    connection_name="granolamcp",
    identifier="user_123",
)
print("Authorize Granola MCP:", auth_link.link)
input("Press Enter after authorizing...")

connected_account = scalekit_client.actions.get_or_create_connected_account(
    connection_name="granolamcp",
    identifier="user_123",
)

tool_response = scalekit_client.actions.execute_tool(
    tool_name="granolamcp_query_granola_meetings",
    connected_account_id=connected_account.connected_account.id,
    tool_input={
        "query": "What decisions and follow-ups came out of last week's customer calls?"
    },
)
print("Granola response:", tool_response)
```

  ### Node.js

```typescript title="examples/granolamcp_query_meetings.ts"

const scalekit = new ScalekitClient(
  process.env.SCALEKIT_ENV_URL!,
  process.env.SCALEKIT_CLIENT_ID!,
  process.env.SCALEKIT_CLIENT_SECRET!
);
const actions = scalekit.actions;

const { link } = await actions.getAuthorizationLink({
  connectionName: 'granolamcp',
  identifier: 'user_123',
});
console.log('Authorize Granola MCP:', link);
process.stdout.write('Press Enter after authorizing...');
await new Promise((resolve) => process.stdin.once('data', resolve));

const connectedAccount = await actions.getOrCreateConnectedAccount({
  connectionName: 'granolamcp',
  identifier: 'user_123',
});

const toolResponse = await actions.executeTool({
  toolName: 'granolamcp_query_granola_meetings',
  connectedAccountId: connectedAccount?.id,
  toolInput: {
    query: "What decisions and follow-ups came out of last week's customer calls?",
  },
});
console.log('Granola response:', toolResponse.data);
```

> tip: Preserve citations
>
> `granolamcp_query_granola_meetings` returns inline citations back to the source meeting notes. Keep those citations in your final user-facing response when possible.

Before calling this connector from your code, create the Granola MCP connection in **AgentKit** > **Connections** and copy the exact **Connection name** from that connection into your code. The value in code must match the dashboard exactly.

## Tool list

Use the exact tool names from the **Tool list** below when you call `execute_tool`. If you're not sure which name to use, list the tools available for the current user first.

## Tool list

### `granolamcp_get_meeting_transcript`

Get the full transcript for a specific Granola meeting by ID. Returns only the verbatim transcript content, not summaries or notes.
Use this when the user needs exact quotes, specific wording, or wants to review what was literally said in a meeting. For summarized content or action items, use query_granola_meetings or list_meetings/get_meetings instead.

Parameters:

- `meeting_id` (`string`, required): Meeting UUID
- `schema_version` (`string`, optional): Optional schema version to use for tool execution
- `tool_version` (`string`, optional): Optional tool version to use for tool execution

### `granolamcp_get_meetings`

Get detailed meeting information for one or more Granola meetings by ID. Returns private notes, AI-generated summary, attendees, and metadata.
Use this when you already have specific meeting IDs (e.g. from list_meetings results). For open-ended questions about meeting content, use query_granola_meetings instead.

Parameters:

- `meeting_ids` (`array`, required): Array of meeting UUIDs (max 10)
- `schema_version` (`string`, optional): Optional schema version to use for tool execution
- `tool_version` (`string`, optional): Optional tool version to use for tool execution

### `granolamcp_list_meetings`

List the user's Granola meeting notes within a time range. Returns meeting titles and metadata.

IMPORTANT: For short-term questions about recent meeting details, prefer using query_granola_meetings instead.

When to use:
- User asks to list their meetings
- User asks about action items, decisions, or summaries from meetings over a longer or specific date range
- User asks about content from their meeting transcripts
- User references 'Granola notes' or 'meeting notes' or 'transcripts'

When NOT to use:
- User is asking about upcoming calendar events or scheduling
- User wants to create/modify calendar invites

Use get_meetings to retrieve detailed meeting content after identifying relevant meetings.

Parameters:

- `custom_end` (`string`, optional): ISO date for custom range end (required if time_range is 'custom')
- `custom_start` (`string`, optional): ISO date for custom range start (required if time_range is 'custom')
- `schema_version` (`string`, optional): Optional schema version to use for tool execution
- `time_range` (`string`, optional): Time range to query meetings from
- `tool_version` (`string`, optional): Optional tool version to use for tool execution

### `granolamcp_query_granola_meetings`

Query Granola about the user's meetings using natural language. Returns a tailored response with inline citation links in mark  (e.g. [[0]](url)) that reference source meeting notes.

IMPORTANT: The response includes numbered citation links to specific Granola meeting notes. These citations MUST be preserved in your response to the user — they provide transparency and allow the user to verify information by clicking through to the original notes.

When to use:
- User asks about what was discussed, decided, or action-items from meetings
- User asks about follow-ups, todos, or commitments from recent meetings
- User references 'Granola notes' or 'meeting notes'

When NOT to use:
- User is asking about calendar scheduling or upcoming events
- User explicitly asks for a specific meeting by ID (use get_meetings instead)

Prioritize using query_granola_meetings over list_meetings/get_meetings for open-ended or natural language queries about meeting content.

Parameters:

- `query` (`string`, required): The query to run on Granola meeting notes
- `document_ids` (`array`, optional): Optional list of specific meeting IDs to limit context to
- `schema_version` (`string`, optional): Optional schema version to use for tool execution
- `tool_version` (`string`, optional): Optional tool version to use for tool execution


---

## More Scalekit documentation

| Resource | What it contains | When to use it |
|----------|-----------------|----------------|
| [/llms.txt](/llms.txt) | Structured index with routing hints per product area | Start here — find which documentation set covers your topic before loading full content |
| [/llms-full.txt](/llms-full.txt) | Complete documentation for all Scalekit products in one file | Use when you need exhaustive context across multiple products or when the topic spans several areas |
| [sitemap-0.xml](https://docs.scalekit.com/sitemap-0.xml) | Full URL list of every documentation page | Use to discover specific page URLs you can fetch for targeted, page-level answers |