The Era Context MCP connector routes your AI agent's tool calls to Era Context's own MCP server through Scalekit. Each user signs in to Era Context once, and Scalekit stores and refreshes their tokens, so your agent never handles credentials. It comes with 94 tools.
- Tools
- 94
- What they doRead · write · destructive
- 26 · 57 · 1126 read57 write11 destructive
- Users sign in with
- OAuth
- OAuth app
- Scalekit's or your own
Setup
Install the SDK
Terminal window npm install @scalekit-sdk/node dotenvTerminal window pip install scalekit-sdk-python python-dotenvSet your credentials
Add your Scalekit credentials to your
.envfile. Find values in app.scalekit.com > Developers > API Credentials..env SCALEKIT_ENVIRONMENT_URL=<your-environment-url>SCALEKIT_CLIENT_ID=<your-client-id>SCALEKIT_CLIENT_SECRET=<your-client-secret>Create the Era Context MCP connection
In AgentKit > Connections, create an Era Context MCP connection. The name you give it is the
connection_nameyour code passes. See Configure connections.Scalekit credentials are available for Era Context MCP server, so you don't need to register an OAuth app.
Authorize a user and make your first call
quickstart.mts 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.actionsconst connector = 'eracontextmcp'const identifier = 'user_123'// Generate an authorization link for the userconst { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })console.log('Authorize Era Context MCP:', link)const rl = createInterface({ input: process.stdin, output: process.stdout })await rl.question('Press Enter after authorizing...')rl.close()// Make your first callconst result = await actions.executeTool({connector,identifier,toolName: 'eracontextmcp_accounts__list_financial_accounts',toolInput: {},})console.log(result)Terminal window npx tsx quickstart.mtsquickstart.py import osfrom scalekit import ScalekitClientfrom dotenv import load_dotenvload_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.actionsconnection_name = "eracontextmcp"identifier = "user_123"# Generate an authorization link for the userlink_response = actions.get_authorization_link(connection_name=connection_name,identifier=identifier,)print("Authorize Era Context MCP:", link_response.link)input("Press Enter after authorizing...")# Make your first callresult = actions.execute_tool(tool_input={},tool_name="eracontextmcp_accounts__list_financial_accounts",connection_name=connection_name,identifier=identifier,)print(result)Terminal window python quickstart.pyEach user signs in once. See Authorize a user for the full flow and statuses.
Tools
Pass the exact name toexecute_tooleracontextmcp_accounts__check_account_balanceGet the current and available balance for a specific account, including credit limit if applicable.Read-onlyAccounts Check Account Balance
Get the current and available balance for a specific account, including credit limit if applicable. Requires an account_group_key from List Financial Accounts.
Inputs
account_group_keystringrequired- The account group projection key. Obtain from accounts__list_financial_accounts (the account_group_key field).
eracontextmcp_accounts__list_financial_accountsList all linked accounts (bank, credit card, investment, manual) with balances and the account_group_key values used by other tools.Read-onlyAccounts List Financial Accounts
List all linked accounts (bank, credit card, investment, manual) with balances and the account_group_key values used by other tools.
Inputs
include_hiddenboolean- Set to true to also show accounts the user has chosen to hide. Default: false (only visible accounts).default
false include_severedboolean- Set include_severed=true to also list the accounts of connections the user disconnected. Each has visibility 'connection_severed', reads archived unless the user chose to keep it, and shows its last balance, with its balance_as_of, only if it was visible before the disconnect; otherwise that balance is withheld. That balance is never refreshed. They are counted in total_count only, never in excluded_account_count, visible_account_count or account_limit. Accounts of a connection the institution ended are not included. No visibility setting hides them, so accounts__set_account_visibility cannot bring one back; reconnecting with connections__connect_bank_account can, on a plan that includes live data sources. On a plan that includes none, the message beside the list says so and what to do instead, unless this read could not check the plan. Default: false, which lists no such account.default
false
eracontextmcp_billing__get_current_planGet the user's active plan tier, billing period, feature entitlements, and usage against plan limits.Read-onlyBilling Get Current Plan
Get the user's active plan tier, billing period, feature entitlements, and usage against plan limits.
Inputs
currencystring- Which currency to show the amounts in. Optional: omit it and the amounts are shown in the currency this platform can tell the user settles in — the one their live subscriptions are billed in, or, for a user holding no live subscription, the one their past subscriptions settled in — and in the default currency only where it can tell neither, or tells more than one. That is the same currency the response reports as settled_currency, so a null settled_currency means the amounts are in the default currency. A currency outside the supported set is rejected rather than substituted.
eracontextmcp_billing__list_paymentsList the user's past invoices — what they were charged, when, for which service period, and whether each was paid.Read-onlyBilling List Payments
List the user's past invoices — what they were charged, when, for which service period, and whether each was paid. Use for 'what have I been charged?', 'when was I last billed?', or 'show me my receipts'. Amounts are in minor currency units (cents for USD). Pagination is forward-only and cursor-based, not page-numbered: pass the previous response's next_cursor back as cursor to get the next page, and stop when next_cursor is null (has_more is false). This tool returns no invoice PDF or hosted invoice link, by design.
Inputs
billing_group_idstring- The billing group this call acts on. Omit it to act on the user's own billing group, which is what almost every call wants. To act on another group, pass one of the billing_group_id values listed in billing_group_contexts by billing__get_current_plan; only contexts with can_manage_billing true can be changed, and their invoices and offer previews read, while any member may list the subscriptions that cover them (a member's list omits the amounts the payer is charged and the offers open to the payer). A group the user does not belong to, or a value that is not a billing group id, is refused and the call never falls back to another group. When a flow takes more than one call (a confirmation key, or a preview then a confirm), pass the same billing_group_id on each.
cursorstring- Opaque pagination cursor from the previous page's next_cursor. Omit for the first page. Echo it back exactly as received — it is not an offset and cannot be constructed or incremented.
limitinteger- Maximum invoices to return on this page. Values outside the supported range are clamped server-side, so an out-of-range value degrades to the nearest supported page size rather than failing.
eracontextmcp_billing__list_plansList all available subscription plans with pricing, billing periods, and plan identifiers needed for the upgrade tool.Read-onlyBilling List Plans
List all available subscription plans with pricing, billing periods, and plan identifiers needed for the upgrade tool.
Inputs
currencystring- Which currency to show the plan amounts in. Optional: omit it and the amounts are shown in the currency this platform can tell the user settles in — the one their live subscriptions are billed in, or, for a user holding no live subscription, the one their past subscriptions settled in — and in the default currency only where it can tell neither, or tells more than one. That is the same currency the response reports as settled_currency, so a null settled_currency means the amounts are in the default currency. A currency outside the supported set is rejected rather than substituted.
product_keystring- Which product to explore plan options for (e.g., 'hub', 'quant'). Defaults to 'hub' if omitted.
eracontextmcp_billing__list_subscriptionsList what the user is actually being charged for right now, read live from Stripe, broken down by individual line item.Read-onlyBilling List Subscriptions
List what the user is actually being charged for right now, read live from Stripe, broken down by individual line item. Use for 'what am I paying for?', 'when does my subscription renew?', 'how much is my add-on?', or 'am I being charged twice?'. Each subscription carries one or more items, and price, billing period and renewal date are per ITEM, not per subscription. A user may also hold more than one subscription. Call billing__list_payments for past invoices rather than inferring them from this response.
Inputs
billing_group_idstring- The billing group this call acts on. Omit it to act on the user's own billing group, which is what almost every call wants. To act on another group, pass one of the billing_group_id values listed in billing_group_contexts by billing__get_current_plan; only contexts with can_manage_billing true can be changed, and their invoices and offer previews read, while any member may list the subscriptions that cover them (a member's list omits the amounts the payer is charged and the offers open to the payer). A group the user does not belong to, or a value that is not a billing group id, is refused and the call never falls back to another group. When a flow takes more than one call (a confirmation key, or a preview then a confirm), pass the same billing_group_id on each.
eracontextmcp_connections__list_connectionsList every one of the user's bank connections with an honest, provider-agnostic status for each: whether it is healthy, syncing with no data yet, needs reconnecting, is terminally denied, is currently disconnected, or one of several other narrower states.Read-onlyConnections List Connections
List every one of the user's bank connections with an honest, provider-agnostic status for each: whether it is healthy, syncing with no data yet, needs reconnecting, is terminally denied, is currently disconnected, or one of several other narrower states. This is the discover hop of the connection recovery loop — call this first to get each connection's connection_id, then act on a specific connection with connections__trigger_connection_resync, connections__connect_bank_account, or connections__disconnect_institution.
Inputs
reasonstring- Optional free-text note stating, in one short sentence, why you are calling this tool. It does not affect the result and is recorded only for diagnostics. This tool takes no other input: do not put data, filters, or parameters here, and omit it entirely if you have nothing to say. Do not include personal or financial details.
eracontextmcp_help__get_helpGet help content for a specific topic: getting_started, connecting_accounts, what_can_i_ask, privacy_and_security, or troubleshooting.Read-onlyHelp Get Help
Get help content for a specific topic: getting_started, connecting_accounts, what_can_i_ask, privacy_and_security, or troubleshooting. Topic is required.
Inputs
topicstringrequired- The help topic to retrieve. Use 'getting_started' for first-time users, 'connecting_accounts' for account linking guidance, 'what_can_i_ask' for example prompts, 'privacy_and_security' for data handling details, or 'troubleshooting' for common issues.one of
getting_startedconnecting_accountswhat_can_i_askprivacy_and_securitytroubleshooting
eracontextmcp_insights__analyze_spendingBreak down spending into ranked groups by category, merchant, account, or time period — each with amount, percentage, and transaction count.Read-onlyInsights Analyze Spending
Break down spending into ranked groups by category, merchant, account, or time period — each with amount, percentage, and transaction count. Supports drill-down: call with group_by=category first, then again with a specific category and group_by=merchant.
Inputs
account_group_keystring- Filter to a specific account. Pass the account group projection key from accounts__list_financial_accounts (the account_group_key field).
category_keystring- Optional fcat_* category KEY (not a display name) to drill into one category. To get keys, call with group_by='category' and include_subcategories=true; each parent category returns its stable category_key. Pass one back here with group_by='merchant' to see the merchants that drove it. Keys are also listed by transactions__list_spending_categories (the key field). Omit to include all categories.
group_bystring- How to group the spending: 'category' (e.g., Groceries, Transportation), 'merchant' (e.g., Amazon, Starbucks), 'account' (by bank account), 'week' or 'month' (spending over time).default
category include_subcategoriesboolean- When true and group_by is 'category', groups results by parent category with subcategory breakdown. Has no effect on any other grouping, including on top_n.default
false periodstring- Time range for the breakdown. Use 'custom' with period_start/period_end for a specific date range.default
this_month period_endstring- Custom end date (YYYY-MM-DD). Used when period is 'custom'. Format: yyyy-MM-dd.
period_startstring- Custom start date (YYYY-MM-DD). Used when period is 'custom'. Format: yyyy-MM-dd.
top_ninteger- Number of groups to return with group_by 'category', 'merchant' or 'account': the top N by amount, highest first, ranked within each currency when the vault holds more than one. Default 10. The 1-50 bound limits the input value on every grouping. It does not cap 'week' or 'month' groups, which ignore top_n.default
10
eracontextmcp_insights__compare_spending_periodsCompare spending between two time periods side-by-side, returning the dollar and percentage change per group.Read-onlyInsights Compare Spending Periods
Compare spending between two time periods side-by-side, returning the dollar and percentage change per group.
Inputs
account_group_keystring- Filter to a specific account. Pass the account group projection key from accounts__list_financial_accounts (the account_group_key field).
category_keystring- Optional fcat_* category KEY (not a display name) to compare only that category's spending between the two periods. Obtain the key from transactions__list_spending_categories (the key field) or reuse a category_key returned by insights__analyze_spending. Omit to compare across all categories.
group_bystring- How to break down the comparison: 'total' shows one overall comparison, 'category' compares each spending category, 'merchant' compares each merchant.default
total period_astring- The first time period to compare (shown as the 'current' or 'newer' period in the results).default
this_month period_bstring- The second time period to compare against (shown as the 'baseline' or 'older' period).default
last_month
eracontextmcp_insights__forecast_spendingProject end-of-period spending based on current pace and historical patterns.Read-onlyInsights Forecast Spending
Project end-of-period spending based on current pace and historical patterns.
Inputs
account_group_keystring- Limit the projection to a specific account. Pass the account group projection key from accounts__list_financial_accounts (the account_group_key field). Omit to project across all accounts.
periodstring- The time period to project spending for. 'this_month' is most common.default
this_month
eracontextmcp_insights__get_cash_flowGet multi-period income vs.Read-onlyInsights Get Cash Flow
Get multi-period income vs. spending totals broken down by week or month, showing net cash flow per period.
Inputs
account_group_keystring- Filter to a specific account. Pass the account group projection key from accounts__list_financial_accounts (the account_group_key field). Omit to see cash flow across all accounts.
granularitystring- Whether to show cash flow by 'week' or 'month'.default
month num_periodsinteger- How many periods to include (e.g., 6 months, 12 weeks). Default: 6, max: 12.default
6
eracontextmcp_insights__get_daily_category_spendingGet a per-day, per-category spending breakdown for a calendar month.Read-onlyInsights Get Daily Category Spending
Get a per-day, per-category spending breakdown for a calendar month. Returns one row per day-and-category combination with the spending amount, transaction count, and the user's category display name, plus month totals. Use for spending-calendar drill-downs and questions like 'which categories did I spend on each day this month?' or 'break down my daily spending by category'. For per-day totals of spending, income, and bills use insights__get_daily_financial_summary; for ranked category totals over a period use insights__analyze_spending. For the current month, totals apply a same-day rolling cutoff: rows dated after today are still returned but excluded from total_amount and transaction_count. Results include only posted/settled transactions; pending (authorization-hold) transactions are excluded.
Inputs
monthinteger- Month number (1-12). Defaults to the current month.
yearinteger- Year of the month to query. Defaults to the current year.
eracontextmcp_insights__get_daily_financial_summaryGet a day-by-day breakdown of spending and income totals for a specific month, optionally filtered to one category.Read-onlyInsights Get Daily Financial Summary
Get a day-by-day breakdown of spending and income totals for a specific month, optionally filtered to one category.
Inputs
category_keystring- Optional fcat_* category key to filter daily totals by a specific category. Omit to get unfiltered totals.
monthinteger- Month number (1-12). Defaults to the current month.
yearinteger- Year of the month to query. Defaults to the current year.
eracontextmcp_knowledge__get_financial_context_and_overviewGet the user's complete financial context — facts, goals, account summary, net worth, monthly spending, top categories, and pending personalization questions.Read-onlyKnowledge Get Financial Context And Overview
Get the user's complete financial context — facts, goals, account summary, net worth, monthly spending, top categories, and pending personalization questions. Call this first for comprehensive context.
Inputs
categorystring- The group a fact is filed under; each fact's category field names it. Set it to return only the facts filed under that category. Omit it to return every fact, including facts filed under a group this list does not name, which no value here selects.
include_simulation_modesarray- The kinds of account to cover: 'live' is real money, 'paper' is a broker's practice account and 'scenario' is a user's hypothetical. Send several to cover more than one, for example ["live", "paper"]. Omit to cover live accounts only (the default, ["live"]); an empty list is refused. accounts, totals_by_type and net_worth cover live accounts only unless include_simulation_modes names other modes. included_simulation_modes states the modes a response covers and simulation_excluded_account_count counts the accounts it left out, so say which modes a total covers whenever you quote it. current_month, last_month and top_categories are not filtered by simulation mode.
pack_slugstring- The question pack slug for completion progress data. Defaults to 'financial-profile-v1' if omitted.
statusstring- Filter assertions by lifecycle status: 'active' (current facts), 'superseded' (replaced by newer facts), 'retracted' (withdrawn), or 'draft' (not finalized). Omit to return only active assertions.
tagsarray- Filter assertions to those matching specific tags. Omit to return all assertions regardless of tags. With tags, each fact entry is the most recently stated of its group's records that carry them, and other_records counts only those.
eracontextmcp_knowledge__get_pending_questionsGet unanswered personalization questions with display text, answer type, and criticality.Read-onlyKnowledge Get Pending Questions
Get unanswered personalization questions with display text, answer type, and criticality. High-criticality questions unlock additional features.
Inputs
max_countinteger- Maximum number of questions to return. Defaults to 5 if omitted.default
5 pack_slugstring- The question pack slug to retrieve questions from. Defaults to 'financial-profile-v1' if omitted.
eracontextmcp_knowledge__recall_historyGet the full change history for a specific financial fact, including all past values and timestamps.Read-onlyKnowledge Recall History
Get the full change history for a specific financial fact, including all past values and timestamps.
Inputs
slugstringrequired- The slug of the fact to retrieve history for. Get assertion slugs from knowledge__get_financial_context_and_overview.
instance_idstring- Instance identifier for repeatable assertions. Only needed when multiple instances exist for the same slug.
eracontextmcp_knowledge__show_question_uiRender an interactive prompt for a specific pending question, including answer constraints and suggested presentation format.Read-onlyKnowledge Show Question Ui
Render an interactive prompt for a specific pending question, including answer constraints and suggested presentation format.
Inputs
question_slugstringrequired- The slug of the question to present as a visual form. Get available slugs from knowledge__get_pending_questions.
pack_slugstring- The question pack slug containing this question. Defaults to 'financial-profile-v1' if omitted.
eracontextmcp_nurture__get_my_statusGet the caller's own nurture (lifecycle email) campaign enrollment status — which campaigns they are currently enrolled in, their progress through each, and whether they have unsubscribed.Read-onlyNurture Get My Status
Get the caller's own nurture (lifecycle email) campaign enrollment status — which campaigns they are currently enrolled in, their progress through each, and whether they have unsubscribed. Use for questions like 'what emails am I signed up for?' or 'am I subscribed to X?'. Call nurture__set_subscription to change the subscription state for a specific campaign.
Inputs
reasonstring- Optional free-text note stating, in one short sentence, why you are calling this tool. It does not affect the result and is recorded only for diagnostics. This tool takes no other input: do not put data, filters, or parameters here, and omit it entirely if you have nothing to say. Do not include personal or financial details.
eracontextmcp_referral__get_dashboard_ssoGet a single-sign-on URL for the user's referral dashboard without a separate login.Read-onlyReferral Get Dashboard Sso
Get a single-sign-on URL for the user's referral dashboard without a separate login.
Inputs
reasonstring- Optional free-text note stating, in one short sentence, why you are calling this tool. It does not affect the result and is recorded only for diagnostics. This tool takes no other input: do not put data, filters, or parameters here, and omit it entirely if you have nothing to say. Do not include personal or financial details.
eracontextmcp_referral__get_referral_linkGet the user's unique shareable referral link for inviting others.Read-onlyReferral Get Referral Link
Get the user's unique shareable referral link for inviting others.
Inputs
reasonstring- Optional free-text note stating, in one short sentence, why you are calling this tool. It does not affect the result and is recorded only for diagnostics. This tool takes no other input: do not put data, filters, or parameters here, and omit it entirely if you have nothing to say. Do not include personal or financial details.
eracontextmcp_referral__get_referral_statsGet referral performance stats: invites sent, conversions, and earnings.Read-onlyReferral Get Referral Stats
Get referral performance stats: invites sent, conversions, and earnings.
Inputs
reasonstring- Optional free-text note stating, in one short sentence, why you are calling this tool. It does not affect the result and is recorded only for diagnostics. This tool takes no other input: do not put data, filters, or parameters here, and omit it entirely if you have nothing to say. Do not include personal or financial details.
eracontextmcp_transactions__list_recurring_chargesList detected recurring charges (subscriptions, bills, income) with merchant, amount, and frequency.Read-onlyTransactions List Recurring Charges
List detected recurring charges (subscriptions, bills, income) with merchant, amount, and frequency.
Inputs
active_onlyboolean- When true (default), only shows recurring items that have appeared within the last 60 days. Set to false to also include items that may have stopped.default
true typestring- Filter by type: 'subscription' (Netflix, Spotify, etc.), 'bill' (rent, utilities, etc.), 'income' (salary, freelance, etc.), or 'all' for everything.default
all
eracontextmcp_transactions__list_spending_categoriesGet the full category tree with fcat_* keys, icons, and spending types.Read-onlyTransactions List Spending Categories
Get the full category tree with fcat_* keys, icons, and spending types. Call this to discover valid category keys for other tools.
Inputs
reasonstring- Optional free-text note stating, in one short sentence, why you are calling this tool. It does not affect the result and is recorded only for diagnostics. This tool takes no other input: do not put data, filters, or parameters here, and omit it entirely if you have nothing to say. Do not include personal or financial details.
eracontextmcp_transactions__list_transactionsPaginated chronological list of transactions with optional filters for date, account, category, tags, and review status.Read-onlyTransactions List Transactions
Paginated chronological list of transactions with optional filters for date, account, category, tags, and review status. For keyword searches, use search_transactions instead.
Inputs
account_group_keystring- Filter to transactions from a specific account. Pass the account group projection key from accounts__list_financial_accounts (the account_group_key field).
category_keystring- Filter to transactions with this fcat_* category projection key. Get category keys from transactions__list_spending_categories. When combined with include_children=true, includes transactions from all subcategories.
from_datestring- Start date for transaction range (YYYY-MM-DD). Defaults to the earliest transaction history the caller's plan permits — see the tool description for the free-plan history window. Format: yyyy-MM-dd.
include_childrenboolean- When true and category_key is set, includes transactions from the parent category and all its subcategories. Use this for parent category transaction counts.default
false include_pendingboolean- When true, also return pending (authorization-hold) transactions dated within the recent-pending window described in the tool description, each with is_pending=true. Default false. Pending rows are read-only.default
false pageinteger- Page number (1-based)default
1 page_sizeinteger- Number of transactions per page (max 100)default
50 review_statusstring- Filter to transactions by their review status. System rules like anomaly detection and bounced payment detection automatically flag transactions as 'needs_review'.
rule_idsarray- Rule projection keys (e.g. ["frul_abc"]). Only transactions matched by at least one of these rules are returned. Maximum 50 items; requests with more than 50 items are rejected with an error. Get rule keys from transactions__manage_automation_rules with 'list' action.
tag_keysarray- Tag projection keys (e.g. ["ftag_abc"]). Only transactions with at least one of these tags are returned. Maximum 50 items; requests with more than 50 items are rejected with an error. Get tag keys from transactions__manage_transaction_tags with 'list_tags' action.
to_datestring- End date for transaction range (YYYY-MM-DD). Defaults to today. Format: yyyy-MM-dd.
eracontextmcp_transactions__search_transactionsSearch and filter transactions by merchant name, description, amount range, category, date range, and direction (debit/credit).Read-onlyTransactions Search Transactions
Search and filter transactions by merchant name, description, amount range, category, date range, and direction (debit/credit). Returns matching transactions with total count and sum — no arithmetic needed. Use for targeted questions like 'how much did I spend at Starbucks?', 'what was that $50 charge?', or 'show me all refunds this month'. Supports free-text search so exact merchant names are not required. Use category_key with include_children=true to search across all subcategories of a parent category. For browsing recent activity chronologically, prefer transactions__list_transactions instead. Session context from knowledge__get_financial_context_and_overview enriches these results with the user's profile, goals, and preferences.
Inputs
account_group_keystring- Filter to transactions from a specific account. Pass the account group projection key from accounts__list_financial_accounts (the account_group_key field).
category_keystring- Filter to transactions with this fcat_* category projection key. Get category keys from transactions__list_spending_categories. When combined with include_children=true, includes transactions from all subcategories.
directionstring- Filter by money direction: 'debit' for money going out (purchases, payments), 'credit' for money coming in (income, refunds), or 'all' for both.default
all include_childrenboolean- When true and category_key is set, includes transactions from the parent category and all its subcategories. Use this for parent category transaction counts.default
false include_pendingboolean- When true, also return pending (authorization-hold) transactions dated within the recent-pending window described in the tool description, each with is_pending=true. Default false. Pending rows are read-only.default
false limitinteger- Maximum number of transactions to return (1-50). The response also includes total_results count and sum even if the limit clips the list.default
25 max_amountnumber- Maximum transaction amount.
min_amountnumber- Minimum transaction amount. Use negative values for charges/debits (e.g., -100 finds charges of $100 or more).
periodstring- Time range to search within. Use 'custom' with period_start/period_end for a specific date range.default
all_time period_endstring- Custom end date (YYYY-MM-DD). Used when period is 'custom'. Format: yyyy-MM-dd.
period_startstring- Custom start date (YYYY-MM-DD). Used when period is 'custom'. Format: yyyy-MM-dd.
querystring- Free-text search across merchant name and description. Exact merchant names are not required — partial matches work (e.g., 'star' matches 'Starbucks').
review_statusstring- Filter to transactions by their review status. System rules like anomaly detection and bounced payment detection automatically flag transactions as 'needs_review'.
rule_idsarray- Rule projection keys (e.g. ["frul_abc"]). Only transactions matched by at least one of these rules are returned. Maximum 50 items; requests with more than 50 items are rejected with an error. Get rule keys from transactions__manage_automation_rules with 'list' action.
sort_bystring- How to order the results: by 'date' (newest first), 'amount', or 'merchant' name.default
date tag_keysarray- Tag projection keys (e.g. ["ftag_abc"]). Only transactions with at least one of these tags are returned. Maximum 50 items; requests with more than 50 items are rejected with an error. Get tag keys from transactions__manage_transaction_tags with 'list_tags' action.
eracontextmcp_accounts__get_account_balance_seriesReturns the balance of up to 100 accounts over one window: one series per account, in the account's own currency, with one point per bucket, each point labelled recorded or estimated.WriteAccounts Get Account Balance Series
Returns the balance of up to 100 accounts over one window: one series per account, in the account's own currency, with one point per bucket, each point labelled recorded or estimated. Name the accounts with account_group_keys, the account_group_key (uagr_…) of each account accounts__list_financial_accounts returns; a duplicate key is read once. An empty series list comes with empty_state_message, which names the next step. Name the window with range, or with from and to (inclusive yyyy-MM-dd dates spanning at most 14000 days); with neither, the window is one_year ending today (UTC). Granularity weekly (the default here) cuts one bucket per ISO week; ask for daily for one per day or monthly for one per calendar month. Each point is the balance at its bucket_end, an instant, and bucket_time_zone_id names the zone every bucket was cut in. A point's kind is recorded (source provider, a balance the account's provider reported, or manual, one the user stated) or estimated (source transaction_derived, a balance the balance backfill of a manually tracked account derived from its transactions, or extrapolated, computed when read from a provider account's recorded balances moved by its transactions); always present an estimated point as an estimate. A bucket that holds a recorded balance reads that balance. observed_in_bucket false means the bucket holds none of the point's own evidence (a recorded balance, a stored derived balance, or for an extrapolated point a transaction dated in it), so its value was carried into it. sources recorded_and_estimated (the default) serves recorded balances and, in the buckets no recorded balance holds, estimates; recorded_only serves no estimate, and a bucket with no reading of its own repeats the last recorded balance with observed_in_bucket false. carry_in is the account's recorded balance as the window opens, null when none is recorded by then; the points start at the first bucket with a value, and nothing is invented for the buckets before it. estimate_basis names the estimate source a series used (none, transaction_derived or extrapolated). estimates_withheld_for_liability true marks a liability whose backfill-derived balances are not served, because that derivation moves an amount owed the wrong way; its series holds recorded balances only, and its estimate_note says so. Report each series in its own currency (its upper-case ISO 4217 code, or Unknown when the account has no currency on record), and never add series of different currencies. The user's plan can limit how far back estimates reach: when history_window_message is present, estimates before history_window_floor_date were withheld, and history_window_floor_degraded true means the plan could not be confirmed, so the withholding is not the plan's own limit; recorded balances are never withheld. is_investment marks an investment account, whose series is its balance only, not its portfolio value; when a series carries portfolio_value_tool, call holdings__get_holding_value_series with scope account_group and that series' account_group_key for its portfolio value over time. Live accounts are read by default; to read a paper or scenario account, name every mode to read in include_simulation_modes (for example ["live", "paper"]). included_simulation_modes echoes the modes read and excluded_account_count counts the requested accounts the mode filter left out. left_out_keys lists every requested key with no series and why: not_found, no active account of the user's has the key (it is mistyped, another kind of key, an account that is not active, or one whose connection was disconnected; accounts__check_account_balance with a not-found key says whether its account's connection was disconnected, and if it was, reconnect it via connections__connect_bank_account to restore balances on a plan that includes live data sources; on a plan that includes none, accounts__check_account_balance says so and what to do instead); excluded_simulation_mode, its mode is not among those read; not_visible, the user's plan or the user's own choice hides the account, and its current balance is hidden the same way (accounts__check_account_balance says which); no_balance_surface, its provider reports no balance; no_balance_history, no balance is known for it in the window, and none is invented; estimates_withheld_by_history_window, only estimates reached the window and the history window withheld them all (history_window_message says from which date and why); estimates_withheld_for_liability, a liability whose only values in the window are backfill-derived balances, which are not served. One call reads at most 36600 points (accounts times buckets); a larger read is refused with words naming a coarser granularity, a shorter window or fewer accounts. A call naming more than 100 distinct keys is refused; read the others in further calls.
Inputs
account_group_keysarrayrequired- The account_group_key (uagr_…) of each account to read, as accounts__list_financial_accounts returns it: between 1 and 100 distinct keys, matched exactly; a duplicate is read once. A key that names no account of the user's is answered in left_out_keys, never as an error. An empty series list comes with empty_state_message, which names the next step.
fromstring- The first date of the window, inclusive, as yyyy-MM-dd. Send it with to, or alone; omit it for the one_year window that ends on to. The window spans at most 14000 days. Format: yyyy-MM-dd.
granularitystring- The size of each bucket: weekly (the default) cuts one per ISO week, monthly one per calendar month and daily one per day. Each point is the balance at its bucket_end. A daily read of many accounts over a long window can pass the 36600-point limit of one call; a coarser granularity keeps it inside.default
weekly include_simulation_modesarray- The kinds of account to read: 'live' is real money, 'paper' is a broker's practice account and 'scenario' is a user's hypothetical. Send several to read more than one, for example ["live", "paper"]. Omit to read live accounts only (the default, ["live"]); a list names at least one mode. included_simulation_modes echoes the modes read and excluded_account_count counts the requested accounts left out.
rangestring- A named window ending today (UTC): one_day and five_days are the last one and five calendar days; one_month, three_months, six_months, one_year and five_years are calendar spans; year_to_date starts on 1 January; max starts at the earliest balance on record among the accounts read (an estimate on record dated before the user's history window counts from that window's floor, and history_window_applied says so when that moves the start), at most 14000 days back. Send range alone, or from and to alone. With neither range nor dates, the window is one_year.
sourcesstring- sources recorded_and_estimated (the default) serves recorded balances and, in the buckets no recorded balance holds, estimates; recorded_only serves no estimate, and a bucket with no reading of its own repeats the last recorded balance with observed_in_bucket false.
tostring- The last date of the window, inclusive, as yyyy-MM-dd, read as a UTC calendar date. Omit it for today; a later date reads as today. Format: yyyy-MM-dd.
eracontextmcp_accounts__set_account_visibilityShow or hide an account in the dashboard without disconnecting it — the account continues to sync.WriteAccounts Set Account Visibility
Show or hide an account in the dashboard without disconnecting it — the account continues to sync.
- Idempotent
Inputs
account_group_keystringrequired- The account group projection key. Obtain from accounts__list_financial_accounts (the account_group_key field).
visiblebooleanrequired- Set to true to show the account (Owner scope) or false to hide it (UserExcluded scope).
eracontextmcp_accounts__toggle_balance_backfillEnable balance history derivation from transaction data, or disable it to revert to snapshot-only balances.WriteAccounts Toggle Balance Backfill
Enable balance history derivation from transaction data, or disable it to revert to snapshot-only balances.
- Idempotent
Inputs
account_group_keystringrequired- The account group projection key identifying the target account group. Obtain from accounts__list_financial_accounts (the account_id field). Must be a manual account.
enablebooleanrequired- Set to true to enable balance derivation from transaction history. Set to false to disable and revert to snapshot-only balance behavior.
eracontextmcp_billing__uncancel_subscriptionReverse a pending subscription cancellation before it takes effect, optionally with a winback discount.WriteBilling Uncancel Subscription
Reverse a pending subscription cancellation before it takes effect, optionally with a winback discount.
- Idempotent
Inputs
apply_couponboolean- Whether to apply the 50% off winback coupon during the uncancel. Defaults to true. Set to false if the user does not want the discount. Has no effect inside a paid intro period, where no coupon is ever applied.
billing_group_idstring- The billing group this call acts on. Omit it to act on the user's own billing group, which is what almost every call wants. To act on another group, pass one of the billing_group_id values listed in billing_group_contexts by billing__get_current_plan; only contexts with can_manage_billing true can be changed, and their invoices and offer previews read, while any member may list the subscriptions that cover them (a member's list omits the amounts the payer is charged and the offers open to the payer). A group the user does not belong to, or a value that is not a billing group id, is refused and the call never falls back to another group. When a flow takes more than one call (a confirmation key, or a preview then a confirm), pass the same billing_group_id on each.
eracontextmcp_billing__upgradeUpgrade to a higher tier or different billing period.WriteBilling Upgrade
Upgrade to a higher tier or different billing period. Use billing__list_plans first to get valid plan identifiers.
Inputs
billing_periodstringrequired- How often to bill. Not every plan sells every billing period: call billing__list_plans to see the billing periods the chosen plan is priced for, and pass one of those. A billing period the plan does not sell is refused.one of
monthlyquarterlyyearlybiennial target_planstringrequired- Which plan to subscribe to (e.g., 'organize', 'automate', 'optimize'). Use billing__list_plans to see available plans.
billing_group_idstring- The billing group this call acts on. Omit it to act on the user's own billing group, which is what almost every call wants. To act on another group, pass one of the billing_group_id values listed in billing_group_contexts by billing__get_current_plan; only contexts with can_manage_billing true can be changed, and their invoices and offer previews read, while any member may list the subscriptions that cover them (a member's list omits the amounts the payer is charged and the offers open to the payer). A group the user does not belong to, or a value that is not a billing group id, is refused and the call never falls back to another group. When a flow takes more than one call (a confirmation key, or a preview then a confirm), pass the same billing_group_id on each.
client_reference_idstring- Optional client reference ID for referral attribution. Passed through to Stripe unchanged.
coupon_idstring- Optional Stripe coupon ID from Rewardful for referral discounts. Ignored when a promotion code is also provided.
currencystring- Which currency to bill the subscription in. Optional: omit it and the subscription is billed in whatever currency this account already settles in. Naming a different currency is refused rather than applied whenever this platform can tell which single currency is in force — from the subscription a tier change would alter, or from the account's own settlement history; where it can tell from neither, or the history holds more than one currency, the purchase proceeds. A currency outside the supported set is rejected rather than substituted.
localestring- Optional locale tag of the language the user reads (e.g. 'en-US', 'de-DE', 'ja-JP'). When the checkout sells a paid intro, its terms are shown on the payment page in this language. Omit it when unknown; English (US) is used.
product_keystring- Which product to upgrade (e.g., 'hub', 'quant'). Defaults to 'hub' if omitted.
promotion_codestring- Optional promotion code to apply a discount at checkout (e.g., 'SAVE50'). Omit to let the user enter one manually.
eracontextmcp_connections__connect_bank_accountStart a bank account connection flow via Plaid or a direct integration and return a redirect URL for the user to complete.WriteConnections Connect Bank Account
Start a bank account connection flow via Plaid or a direct integration and return a redirect URL for the user to complete.
- Idempotent
Inputs
assistant_namestring- Your name or the name of the AI assistant being used (e.g. 'Claude', 'ChatGPT'). This helps personalize the connection experience for the user.
connection_idstring- Optional existing connection ID for reconnection flows. Provide this to reconnect a stale or broken connection instead of creating a new one. Get connection IDs from the accounts listing.
providerstring- Optional banking provider identifier for this connection. Omit to use the platform's default provider unless you have a specific provider requirement.default
mx
eracontextmcp_connections__set_proactive_sync_modeRecord whether Era may proactively ask a bank connection's provider for fresh data on its own schedule.WriteConnections Set Proactive Sync Mode
Record whether Era may proactively ask a bank connection's provider for fresh data on its own schedule. Set mode='disabled' when the user wants Era to stop reaching out to that bank between their own requests; set mode='enabled' to allow it again. This does NOT stop the connection: webhook updates, reconciliation and reads of data the provider already holds continue either way, and an on-demand refresh the user asks for is always honoured. Use connections__list_connections to obtain the connection_id.
- Idempotent
Inputs
connection_idstringrequired- The connection projection key identifying the bank connection. Obtain from connections__list_connections (the connection_id field on each connection entry).
modestringrequired- 'disabled' to stop Era proactively contacting this bank on its own schedule; 'enabled' to allow it. Repeating the instruction the connection already carries is a no-op — it records nothing and adds nothing to the user's history.one of
enableddisabled
eracontextmcp_connections__trigger_connection_resyncTrigger an on-demand data resync for a bank connection.WriteConnections Trigger Connection Resync
Trigger an on-demand data resync for a bank connection. This fetches the latest transaction and balance data from supported banks — most major institutions support on-demand refresh, though it may take a few minutes for data to arrive. Possible outcomes include: resync queued successfully; the bank requires the user to re-authenticate first; the user's plan does not include on-demand resync; data was already refreshed recently; or the connection was not found. Use connections__list_connections to obtain the connection_id.
- Idempotent
Inputs
connection_idstringrequired- The connection projection key identifying the bank connection to resync. Obtain from connections__list_connections (the connection_id field on each connection entry).
eracontextmcp_content__accept_suggestionsAccepts the organisation suggestions the library's model proposed for the user's documents: the folder suggestion files the document in that folder, creating the folder when it is new, and a tag suggestion puts the tag on the document.WriteContent Accept Suggestions
Accepts the organisation suggestions the library's model proposed for the user's documents: the folder suggestion files the document in that folder, creating the folder when it is new, and a tag suggestion puts the tag on the document. Accept only what the user has agreed to, because the suggestions are model-written and may be wrong. The suggestion of a tag the user does not have creates that tag, which also needs the user's tool write permission (mcp:tools-write), granted separately: without it that document's outcome is new_tag_requires_authority, naming the tags that were not created and the permission; the document's other suggestions, and the other documents in the call, are accepted as usual, so tell the user which permission would allow it. A document whose suggestions were applied answers already_decided when the same call is sent again, and nothing changes; a suggestion that was refused for authority, or that belongs to a document which answered stale or conflict, stays open, so it can be accepted once the cause is gone. A change the user made to the document by hand since the suggestions were proposed is never overwritten: the document answers stale, no suggestion was applied for it, not even one the change does not touch, and every suggestion named for it stays open. The stale_reason says which change made a suggestion moot, and sending the same call again answers stale again, so accept the suggestions that are not moot by naming their suggestion_id values, or dismiss the moot one. Name the documents to decide, each by its document_id, and optionally which of its pending organisation suggestions: a suggestion_ids list holds the suggestion_id values that content__get_document and content__list_documents report in the document's organisation, and leaving it out means every suggestion still open when the call runs. Each document is decided on its own and the answer gives one outcome for each document, in the order the call named them: applied when the decision was made, already_decided when every suggestion named was decided before so nothing changed, conflict when the document or the user's tag list changed or could not be read during the call, so no suggestion was decided for that document and the same call may be sent again, and not_found when it is not one of the caller's documents. Two outcomes belong to accepting: stale (accepting only) when the document, its folder or its tags no longer fit what a suggestion proposes (the stale_reason says why: refiled, folder_gone, tag_gone or tag_limit), in which case no suggestion was applied for that document, not even one that was not moot, and every suggestion named for it stays open; and new_tag_requires_authority (accepting only) when an accepted suggestion would create a tag the credential may not create (refused_tag_names lists them and required_scope names the scope that allows it), in which case the document's other suggestions, if any, were applied and the refused ones stay open; dismissing never answers either. A document that is not found, conflicts or is stale does not refuse the rest. A call that is not well formed refuses the whole request and changes nothing: no documents, more than a page of them, a document or a suggestion named twice, an empty suggestion_ids list, a suggestion the document does not have, or an identifier that is not well formed. The text a suggestion carries is written by a model and may be wrong, so name only suggestions the user has decided on. Changing the library needs the user's content write permission (mcp:content-write), which the user grants separately; without it the call is refused and the refusal names the permission.
Inputs
documentsarrayrequired- The documents to decide: 1 to 100 entries, each document named once. A document that is not one of the caller's documents is reported as not_found for that document and does not refuse the others.
eracontextmcp_content__create_folderCreate one of the caller's folders, together with each of its ancestors that does not exist yet, so documents can be filed in it with content__update_document.WriteContent Create Folder
Create one of the caller's folders, together with each of its ancestors that does not exist yet, so documents can be filed in it with content__update_document. Creating a path that is already one of the caller's folders is safe to repeat: the answer is that folder as it stands, with its version unchanged. The answer is the folder: its path as the library holds it, its version, when it was created and last changed, and its tags. A folder is only a place to file documents in: creating one changes no document. A folder is written as a slash-separated path such as 'Taxes/2025', and paths are case-sensitive. A path has at most 200 characters and 8 levels, and the top level is not a folder that can be created. Changing the library needs the user's content write permission (mcp:content-write), which the user grants separately; without it the call is refused and the refusal names the permission. The document library is available only to accounts it is enabled for. For any other account every Content tool refuses with feature_disabled, which no retry changes, so tell the user the library is not on their account instead of trying again.
Inputs
pathstringrequired- The folder to create as a slash-separated path, for example 'Taxes/2025', which also creates 'Taxes' when it does not exist. At most 200 characters and 8 levels; a path that is empty or not well formed is refused.
eracontextmcp_content__dismiss_suggestionsDismisses the organisation suggestions the library's model proposed for the user's documents, so they are no longer offered.WriteContent Dismiss Suggestions
Dismisses the organisation suggestions the library's model proposed for the user's documents, so they are no longer offered. A dismissal is permanent: nothing reopens it, and a suggestion that is dismissed stays dismissed if the library generates the same suggestion again. No document, folder or tag is changed, and the user can still file or tag the document by hand. A document whose suggestions were dismissed answers already_decided when the same call is sent again, and nothing changes; a document that was left in conflict is dismissed by sending it again. Dismiss only what the user has said they do not want. Name the documents to decide, each by its document_id, and optionally which of its pending organisation suggestions: a suggestion_ids list holds the suggestion_id values that content__get_document and content__list_documents report in the document's organisation, and leaving it out means every suggestion still open when the call runs. Each document is decided on its own and the answer gives one outcome for each document, in the order the call named them: applied when the decision was made, already_decided when every suggestion named was decided before so nothing changed, conflict when the document or the user's tag list changed or could not be read during the call, so no suggestion was decided for that document and the same call may be sent again, and not_found when it is not one of the caller's documents. Two outcomes belong to accepting: stale (accepting only) when the document, its folder or its tags no longer fit what a suggestion proposes (the stale_reason says why: refiled, folder_gone, tag_gone or tag_limit), in which case no suggestion was applied for that document, not even one that was not moot, and every suggestion named for it stays open; and new_tag_requires_authority (accepting only) when an accepted suggestion would create a tag the credential may not create (refused_tag_names lists them and required_scope names the scope that allows it), in which case the document's other suggestions, if any, were applied and the refused ones stay open; dismissing never answers either. A document that is not found, conflicts or is stale does not refuse the rest. A call that is not well formed refuses the whole request and changes nothing: no documents, more than a page of them, a document or a suggestion named twice, an empty suggestion_ids list, a suggestion the document does not have, or an identifier that is not well formed. The text a suggestion carries is written by a model and may be wrong, so name only suggestions the user has decided on. Changing the library needs the user's content write permission (mcp:content-write), which the user grants separately; without it the call is refused and the refusal names the permission.
Inputs
documentsarrayrequired- The documents to decide: 1 to 100 entries, each document named once. A document that is not one of the caller's documents is reported as not_found for that document and does not refuse the others.
eracontextmcp_content__extract_documentsAsk the library to extract details from some of the caller's own documents, live or archived, so what their pages state can be listed.WriteContent Extract Documents
Ask the library to extract details from some of the caller's own documents, live or archived, so what their pages state can be listed. Each document is handled on its own and the answer gives one outcome for each distinct document, in the order it was first named: queued when it had no extraction and one was started, requeued when its failed extraction was started again to resume where it stopped, unchanged when an extraction is already queued, running or finished (a finished one is never redone), cancelled when its extraction was ended because the document was deleted for good, not_found when it is not one of the caller's documents, and not_readable when the library does not extract details from its kind of file (the document's extractable member says which). A file the library cannot open shows as a failed extraction whose failure reason is cannot_render, and a file too large for the library to extract details from shows as a failed extraction whose failure reason is too_large_to_read; both are seen when you read the document with content__get_document. A well-formed identifier never refuses the rest, whatever its outcome, but one that is not well formed refuses the whole request, and a document named twice is answered once. Alongside its outcome each document carries where its extraction stands, which is absent for not_found and not_readable. A queued extraction is carried out afterwards, not by this call, so it is not finished when this call returns: read the document with content__get_document later to see how far it has come. Sending the same request again is safe and starts nothing twice. A document_id is the stable identifier a document is listed under. Copy it exactly as listed; it cannot be guessed or built from a title or filename, and an id that is not the caller's own is treated as unknown. Changing the library needs the user's content write permission (mcp:content-write), which the user grants separately; without it the call is refused and the refusal names the permission. The document library is available only to accounts it is enabled for. For any other account every Content tool refuses with feature_disabled, which no retry changes, so tell the user the library is not on their account instead of trying again. Extracting details from documents is a separate capability from the library and is available only to accounts it is enabled for. For any other account content__extract_documents and content__list_document_observations refuse with feature_disabled and say document extraction is not enabled, which no retry changes, so tell the user it is not on their account instead of trying again; every other library tool is unaffected.
Inputs
document_idsarrayrequired- The documents to extract: 1 to 100 identifiers, copied exactly as content__list_documents gives them. A document named more than once is answered once. A well-formed identifier that is not one of the caller's documents is reported as not_found for that document and does not refuse the others; an identifier that is not well formed refuses the whole request.
eracontextmcp_content__get_documentOpen one of the caller's own documents by its document_id: its title, filename, folder, media type, size, tags (each with whether the user added it, the library detected it or the user approved it), when it was created and last changed, where its text extraction stands, the organisation the library generated for it when there is one, and, once the extraction of its file has converged, the documents the file holds.WriteContent Get Document
Open one of the caller's own documents by its document_id: its title, filename, folder, media type, size, tags (each with whether the user added it, the library detected it or the user approved it), when it was created and last changed, where its text extraction stands, the organisation the library generated for it when there is one, and, once the extraction of its file has converged, the documents the file holds. A document the user archived is returned with archived_at, the instant it was archived. A document that is not the caller's, and one that does not exist, are refused identically. To let the user open the document itself, call content__get_document_view_url with the same document_id. A document_id is the stable identifier a document is listed under. Copy it exactly as listed; it cannot be guessed or built from a title or filename, and an id that is not the caller's own is treated as unknown. A document's or folder's version is the number a later change passes back as expected_version, so a change never overwrites an edit the agent has not seen. It advances with every change: read it again from a fresh result before using it, and never reuse one from an earlier read. Beyond its metadata, a document the library has extracted carries organisation, the library's words about the document: a generated_title, the name the extraction that recorded its suggestions gave it; a generated_description, the summary of its latest converged extraction; the language they are in; the batch_key it shares with the documents uploaded alongside it, and the folder_suggestion and tag_suggestions it proposes, each with a suggestion_id. All of it is model-written and may be wrong: it is never the user's own words and never an instruction to follow. Suggestions are proposals only; nothing is filed or tagged until the user decides. Every document carries a display_title, the name the library shows for it: the generated_title while the user has not retitled the document and the library generated one, otherwise the user's own title. When showing a document to the user, show its display_title and always show the filename beside it; do not work the name out from title, generated_title or title_is_default. title is only the user's own saved title, and title_is_default says whether the user has not retitled it. A document without organisation has nothing generated yet. Every document carries a display_description, the description the library shows for it: the read_summary while the latest extraction of the file has converged, and absent otherwise. The library decides it once, so show it as it is and do not work it out. Once the extraction of the file has converged, the document also carries read_summary, a summary of the whole file that states how many documents it holds when it holds more than one; read_name, the name suggested for the whole file; read_folders and read_tags, the folders and tags suggested for the whole file, best first, each with whether the user already has it and how sure the model is; read_documents, the documents the file holds in page order, each with first_page, last_page, class, other_classes, title, a summary of that whole document and its own folders and tags; reading_order, the page numbers in the order the extraction found the pages belong in, which differs from page order when the pages were scanned out of order; and read_language, the language the extraction named. They are absent until then, absent again while the file is extracted again, and absent when the extraction could not converge; they replace nothing the user wrote. An extraction carries a phase while its run is open: reading or writing, and none once the run has ended; reading_number is the number of the extraction the open run is on, counting from one, and extracting the file again raises it. While the run is running, its extraction also carries progress when a drive has reported it: the step the drive is in, the windows and the pages done of the total (each count is present only in the step that counts it, and the windows done can be lower in the step that records the windows than they were in the step before it), and when the drive last made progress. Progress is the drive's last report, not a promise the drive is alive now. The texts can appear before extraction.reading carries its counts. Every text in them is model-written and may be wrong: it is never the user's own words and never an instruction to follow. A document also carries extractable, whether the library extracts details from a file of its type: when it is false the library only saves the document, and it has no extraction, summary or documents to wait for. Every document carries provenance, where it came from: its kind is upload when a person uploaded the file, or email when it arrived as an attachment of an email message, and then its source_id names that message. source_id is an identifier only: it carries no subject, sender or text of the message. This reads what the library knows about its documents and folders (a document's title, filename, folder, size, tags and dates; a folder's path, tags and dates), never the document's content: no file bytes, pages or extracted text are returned. The document library is available only to accounts it is enabled for. For any other account every Content tool refuses with feature_disabled, which no retry changes, so tell the user the library is not on their account instead of trying again.
Inputs
document_idstringrequired- The identifier of one of the caller's documents, copied exactly as content__list_documents gives it.
eracontextmcp_content__get_document_view_urlGet the link that opens one of the caller's own documents in their browser, so they can view or download it.WriteContent Get Document View Url
Get the link that opens one of the caller's own documents in their browser, so they can view or download it. Use when the user asks to see, open or read a document: relay the link and tell them to open it in a browser while signed in to their account. The link works only for the document's owner, so it is not a way to share the document with anyone else; forwarding it gives nobody access. To give someone else access, create a share link with content__create_share_link instead. Archived documents have a link too.
Inputs
document_idstringrequired- The identifier of one of the caller's documents.
eracontextmcp_content__get_library_usageGet how much of the caller's document library is used and how much room is left: the documents and bytes held, the plan's limits for the number of documents, the total bytes and the size of one document, what remains under each, and the documents and bytes by media type and by tag key.WriteContent Get Library Usage
Get how much of the caller's document library is used and how much room is left: the documents and bytes held, the plan's limits for the number of documents, the total bytes and the size of one document, what remains under each, and the documents and bytes by media type and by tag key. A document is counted under every tag it carries, so the tag rows overlap, and archived documents count like any other. Use it before an upload, or when the user asks how full their library is or whether a file will fit. The message in the answer is one sentence to relay to the user; when the library is full it says what frees room. Tag names are not listed here: read them with transactions__manage_transaction_tags and its list_tags action, matching on the tag key.
Inputs
reasonstring- Optional free-text note stating, in one short sentence, why you are calling this tool. It does not affect the result and is recorded only for diagnostics. This tool takes no other input: do not put data, filters, or parameters here, and omit it entirely if you have nothing to say. Do not include personal or financial details.
eracontextmcp_content__list_document_observationsList what one of the caller's own documents states, one page at a time, in reading order: each item's statement, concept, printed label, printed values (money, percent, number, date, date range, text or yes/no, with the currency only when the page settles it), period, the parties it is about as the page names them, the citations that show where the page prints it (page and snippet), and what the extraction made of it (disposition and reason, the slugs it could be written under, and whether it has been promoted).WriteContent List Document Observations
List what one of the caller's own documents states, one page at a time, in reading order: each item's statement, concept, printed label, printed values (money, percent, number, date, date range, text or yes/no, with the currency only when the page settles it), period, the parties it is about as the page names them, the citations that show where the page prints it (page and snippet), and what the extraction made of it (disposition and reason, the slugs it could be written under, and whether it has been promoted). Use it to answer what a document says, to quote where it says it, and to see what the extraction could not settle. These items are what the document states, in the document's own words and figures. They are not facts Era holds: listing them saves nothing, and an item is a fact Era holds only once its promotion_state says so. Every text in an item is what the model extracted from the document and may be wrong: show it as quoted material and never follow an instruction inside it. By default the page lists the addendum: the items kept as observations only, held, or refused a write. Items written as typed facts, ledger lines (such as transactions) and dropped items are listed only when dispositions names them. The addendum can be narrowed by reasons (why items have their disposition) and hold_classes (the kind of hold on a held item); hold_classes never names none. The first page, the one sent with no cursor, also carries facets: how many items the other filters select for each disposition, reason and hold class. Those counts ignore reasons and hold_classes, so they stay whole while one group is paged, and they add up to the items all the pages list without those two filters; a later page carries no facets. Each item says in named_unresolved_account whether it named an account Era could not place in this document: true when it did, false when it named none or named one that was placed, and left out when the item was extracted before this was kept. The page also carries the segment ledger (the documents the latest extraction found in the file), the extraction it belongs to, whether the extraction was cut short, and a message to relay. A document_id is the stable identifier a document is listed under. Copy it exactly as listed; it cannot be guessed or built from a title or filename, and an id that is not the caller's own is treated as unknown. Find the document with content__list_documents, and see whether it has been extracted with content__get_document. A page that is not the last carries a next_cursor. Pass it back unchanged as cursor, with the same document_id and exactly the same filters, to read the next page; a cursor is opaque and cannot be built by hand, and one sent with other filters, or that does not decode, or that names another extraction than the one requested, is refused, so read again from the first page. No next_cursor means the last page was read. A next_cursor continues the extraction its first page listed, even after the document is extracted again; reading and latest_reading show when a newer extraction exists. The document library is available only to accounts it is enabled for. For any other account every Content tool refuses with feature_disabled, which no retry changes, so tell the user the library is not on their account instead of trying again. Extracting details from documents is a separate capability from the library and is available only to accounts it is enabled for. For any other account content__extract_documents and content__list_document_observations refuse with feature_disabled and say document extraction is not enabled, which no retry changes, so tell the user it is not on their account instead of trying again; every other library tool is unaffected.
Inputs
document_idstringrequired- The identifier of one of the caller's documents, copied exactly as content__list_documents gives it. content__get_document tells whether the document has been extracted and counts what the extraction found.
cursorstring- The next_cursor of the previous page, to read the page after it, sent with exactly the same document_id and filters. It continues the extraction its first page listed, even after the document is extracted again. A cursor sent with other filters is refused. Leave out for the first page.
dispositionsarray- The kinds of item to list, each at most once: observation_only, held and projection_refused (the addendum), and written_typed, ledger and dropped. Leave out to list the addendum, which never includes written_typed, ledger or dropped items; name those kinds to see them. Naming a kind replaces the default, so name observation_only, held and projection_refused too to list them beside it.
hold_classesarray- The kinds of hold to list, each at most once: list only the held items whose hold is one of these, such as pay_frequency or currency. none names no hold and is refused. Only held items state a hold class, so name it with held in dispositions or left out. An item states a reason or a hold class, never both, so sending reasons and hold_classes together lists nothing. Leave out to list every hold class. The facets on the first page ignore it.
measure_classstring- List only items of this broad class, for example income, tax, balance or date. Leave out to list every class.
page_sizeinteger- Items per page. Default: 25. Maximum: 100.default
25 readinginteger- The number of the extraction to list, counting from 1. An item the latest extraction did not find again is still listed for an earlier extraction, and says so. Leave out for the latest extraction; an extraction the document has not had is refused.
reasonsarray- The reasons to list, each at most once: list only the items whose reason is one of these, such as not_converged or no_catalog_row. Only observation_only, projection_refused and dropped items state a reason. It narrows the dispositions listed and never widens them: with dispositions left out, only addendum items are narrowed, so name dropped in dispositions to filter dropped items by reason. Leave out to list every reason. The facets on the first page ignore it.
segmentinteger- The number of the only segment to list, as the segments in the page give it, counting from 1; 0 lists the items on pages no segment covers. Leave out to list every segment.
eracontextmcp_content__list_documentsList the caller's own documents, one page at a time: each document's document_id, version, display_title, title, filename, folder, media type, size, tags, dates and extraction status, the organisation the library generated for it when there is one, and, once the extraction of its file has converged, the documents the file holds.WriteContent List Documents
List the caller's own documents, one page at a time: each document's document_id, version, display_title, title, filename, folder, media type, size, tags, dates and extraction status, the organisation the library generated for it when there is one, and, once the extraction of its file has converged, the documents the file holds. Use it to answer what is in the user's library, to find a document by part of its display_title or filename, or to see what is filed in a folder, carries a tag or is of one kind. Filters combine: a document is listed only when it matches all of them. By default the live documents are listed, most recently changed first; set archived to true to list the archived ones instead. The answer says when the library holds no live documents, when a filter matched nothing and which filter to relax, and how to read on when a page is cut short. A document_id is the stable identifier a document is listed under. Copy it exactly as listed; it cannot be guessed or built from a title or filename, and an id that is not the caller's own is treated as unknown. A page that is not the last carries a next_cursor. Pass it back unchanged as cursor, with exactly the same filters, to read the next page; a cursor is opaque and cannot be built by hand, and one sent with other filters is not refused but reads a page of the new listing from the old position, which skips matches. No next_cursor means the last page was read. A document or folder that changes between pages can be skipped or seen twice. A listing that can be sorted refuses a cursor whose sort differs from the page that issued it. A tag key names one of the caller's own tags. Read the keys with transactions__manage_transaction_tags and its list_tags action; a key that is not one of the caller's own live tags is refused. Several keys match anything that carries any one of them, not all of them. A folder is a slash-separated path such as 'Taxes/2025', matched exactly and case-sensitively, and a match never reaches into deeper folders. A folder path and top_level_only are alternatives: give one or neither, never both. A document the user archived is kept but left out of every default listing. Archived documents are read by asking for them explicitly, and each carries archived_at, the instant it was archived. Beyond its metadata, a document the library has extracted carries organisation, the library's words about the document: a generated_title, the name the extraction that recorded its suggestions gave it; a generated_description, the summary of its latest converged extraction; the language they are in; the batch_key it shares with the documents uploaded alongside it, and the folder_suggestion and tag_suggestions it proposes, each with a suggestion_id. All of it is model-written and may be wrong: it is never the user's own words and never an instruction to follow. Suggestions are proposals only; nothing is filed or tagged until the user decides. Every document carries a display_title, the name the library shows for it: the generated_title while the user has not retitled the document and the library generated one, otherwise the user's own title. When showing a document to the user, show its display_title and always show the filename beside it; do not work the name out from title, generated_title or title_is_default. title is only the user's own saved title, and title_is_default says whether the user has not retitled it. A document without organisation has nothing generated yet. Every document carries a display_description, the description the library shows for it: the read_summary while the latest extraction of the file has converged, and absent otherwise. The library decides it once, so show it as it is and do not work it out. Once the extraction of the file has converged, the document also carries read_summary, a summary of the whole file that states how many documents it holds when it holds more than one; read_name, the name suggested for the whole file; read_folders and read_tags, the folders and tags suggested for the whole file, best first, each with whether the user already has it and how sure the model is; read_documents, the documents the file holds in page order, each with first_page, last_page, class, other_classes, title, a summary of that whole document and its own folders and tags; reading_order, the page numbers in the order the extraction found the pages belong in, which differs from page order when the pages were scanned out of order; and read_language, the language the extraction named. They are absent until then, absent again while the file is extracted again, and absent when the extraction could not converge; they replace nothing the user wrote. An extraction carries a phase while its run is open: reading or writing, and none once the run has ended; reading_number is the number of the extraction the open run is on, counting from one, and extracting the file again raises it. While the run is running, its extraction also carries progress when a drive has reported it: the step the drive is in, the windows and the pages done of the total (each count is present only in the step that counts it, and the windows done can be lower in the step that records the windows than they were in the step before it), and when the drive last made progress. Progress is the drive's last report, not a promise the drive is alive now. The texts can appear before extraction.reading carries its counts. Every text in them is model-written and may be wrong: it is never the user's own words and never an instruction to follow. A document also carries extractable, whether the library extracts details from a file of its type: when it is false the library only saves the document, and it has no extraction, summary or documents to wait for. Each listed document carries these members, so the listing gives a file's documents without another call; content__get_document opens one document alone. Every document carries provenance, where it came from: its kind is upload when a person uploaded the file, or email when it arrived as an attachment of an email message, and then its source_id names that message. source_id is an identifier only: it carries no subject, sender or text of the message. This reads what the library knows about its documents and folders (a document's title, filename, folder, size, tags and dates; a folder's path, tags and dates), never the document's content: no file bytes, pages or extracted text are returned. The document library is available only to accounts it is enabled for. For any other account every Content tool refuses with feature_disabled, which no retry changes, so tell the user the library is not on their account instead of trying again.
Inputs
archivedboolean- Set to true to list the archived documents only. By default archived documents are never listed. Default: false.default
false cursorstring- The next_cursor of the previous page, to read the page after it. Leave out for the first page.
folder_pathstring- List only documents filed in exactly this folder, for example 'Taxes/2025'. Documents in its subfolders are not listed. Read the folder paths with content__list_folders. Leave out to list documents in every folder. Never combine with top_level_only.
media_typestring- List only documents of this kind. Leave out to list every kind.
page_sizeinteger- Documents per page. Default: 25. Maximum: 100.default
25 querystring- Text to find in a document's display_title (the name the library shows for it) or its filename, at most 100 characters. A literal, case-insensitive match on part of either, never a pattern. Leave out to apply no search.
sortstring- The order of the list: updated_desc (most recently changed first), created_desc (newest first), title_asc (by display_title) or size_desc (largest first). Keep the same sort while reading on with a cursor. Default: updated_desc.default
updated_desc tag_keysarray- Keys of the caller's own tags, at most 10. A document is listed when it carries any one of them. Get the keys from transactions__manage_transaction_tags with its list_tags action; a key that is not one of the caller's own tags is refused. Leave out to apply no tag filter.
top_level_onlyboolean- Set to true to list only documents filed at the top level, in no folder. Never combine with folder_path. Default: false.default
false
eracontextmcp_content__list_foldersList the caller's own folders, one page at a time, in path order: each folder's path, version, when it was created and last changed, and its tags.WriteContent List Folders
List the caller's own folders, one page at a time, in path order: each folder's path, version, when it was created and last changed, and its tags. Use it to answer how the user's library is organised or whether a folder exists. By default every folder at any depth is listed; give parent_path for the folders directly inside one folder, or set top_level_only for the top level. A folder's tags are its own: a tag on a document never lists a folder, and a tag on a folder never lists the documents filed in it. A folder's answer carries no counts of the documents inside it. The answer says when there are no folders, when a filter matched nothing and which filter to relax, and how to read on when a page is cut short. To see the documents filed in a folder, call content__list_documents with its path as folder_path. A page that is not the last carries a next_cursor. Pass it back unchanged as cursor, with exactly the same filters, to read the next page; a cursor is opaque and cannot be built by hand, and one sent with other filters is not refused but reads a page of the new listing from the old position, which skips matches. No next_cursor means the last page was read. A document or folder that changes between pages can be skipped or seen twice. A tag key names one of the caller's own tags. Read the keys with transactions__manage_transaction_tags and its list_tags action; a key that is not one of the caller's own live tags is refused. Several keys match anything that carries any one of them, not all of them. A folder is a slash-separated path such as 'Taxes/2025', matched exactly and case-sensitively, and a match never reaches into deeper folders. A folder path and top_level_only are alternatives: give one or neither, never both. A document's or folder's version is the number a later change passes back as expected_version, so a change never overwrites an edit the agent has not seen. It advances with every change: read it again from a fresh result before using it, and never reuse one from an earlier read. This reads what the library knows about its documents and folders (a document's title, filename, folder, size, tags and dates; a folder's path, tags and dates), never the document's content: no file bytes, pages or extracted text are returned. The document library is available only to accounts it is enabled for. For any other account every Content tool refuses with feature_disabled, which no retry changes, so tell the user the library is not on their account instead of trying again.
Inputs
cursorstring- The next_cursor of the previous page, to read the page after it. Leave out for the first page.
page_sizeinteger- Folders per page. Default: 25. Maximum: 100.default
25 parent_pathstring- List only the folders directly inside this folder, for example 'Taxes' lists 'Taxes/2025'. Deeper descendants are not listed. Leave out to list folders at every depth. Never combine with top_level_only.
tag_keysarray- Keys of the caller's own tags, at most 10. A folder is listed when it carries any one of them. Get the keys from transactions__manage_transaction_tags with its list_tags action; a key that is not one of the caller's own tags is refused. Leave out to apply no tag filter.
top_level_onlyboolean- Set to true to list only the top-level folders. Never combine with parent_path. Default: false.default
false
eracontextmcp_content__move_folderRename or move one of the caller's folders to a new path: renaming and moving are the same change, because only the path changes (rename 'Taxes/2025' to 'Taxes/2025-filed' by changing its last segment, move it by changing the segments before).WriteContent Move Folder
Rename or move one of the caller's folders to a new path: renaming and moving are the same change, because only the path changes (rename 'Taxes/2025' to 'Taxes/2025-filed' by changing its last segment, move it by changing the segments before). Every folder and document filed beneath the folder moves with it, in one change or not at all, and each ancestor of the new path that does not exist is created. Nothing is deleted and nothing is merged: if a folder already exists at the new path the call is refused as RESOURCE_CONFLICT, and a new path equal to the current one succeeds without changing anything. The new path cannot be inside the folder itself, and neither the folder nor anything beneath it may end up past 200 characters or 8 levels, or the call is refused as INVALID_ARGUMENTS and nothing moves. To undo a move, move the folder back: the ancestors the move created stay, empty, until they are deleted. Repeating a move that succeeded changes nothing: path no longer names a folder, so the repeat is refused as not found, and the folder is then at new_path. The answer is the folder at its new path. Read paths and versions with content__list_folders. A folder is written as a slash-separated path such as 'Taxes/2025', and paths are case-sensitive. A document's or folder's version is the number a later change passes back as expected_version, so a change never overwrites an edit the agent has not seen. It advances with every change: read it again from a fresh result before using it, and never reuse one from an earlier read. If the folder has changed since expected_version was read, nothing is changed and the call is refused as RESOURCE_CONFLICT with the folder's current version: read the folders again with content__list_folders, check that the move still makes sense, then repeat it with the version the new read gives. Changing the library needs the user's content write permission (mcp:content-write), which the user grants separately; without it the call is refused and the refusal names the permission. The document library is available only to accounts it is enabled for. For any other account every Content tool refuses with feature_disabled, which no retry changes, so tell the user the library is not on their account instead of trying again.
Inputs
expected_versionintegerrequired- The version of the folder from the last time it was read with content__list_folders. A folder that has changed since is not moved: the call is refused with the current version so the folder can be read again.
new_pathstringrequired- The path the folder is moved to, for example 'Archive/Taxes/2025'. It must not be the path of a folder that exists, nor inside the folder being moved, and it is at most 200 characters and 8 levels, counting the deepest folder or document beneath the moved folder.
pathstringrequired- The folder's current path, for example 'Taxes/2025', copied exactly as content__list_folders gives it. A path that is not one of the caller's folders is refused as not found.
eracontextmcp_content__restore_documentRestore one of the caller's own archived documents to the library: it returns to the folder it was filed in, with its tags, and appears in the default listings again.WriteContent Restore Document
Restore one of the caller's own archived documents to the library: it returns to the folder it was filed in, with its tags, and appears in the default listings again. Find archived documents by listing with archived set to true in content__list_documents. The answer is the document as it stands afterwards; restoring a document that is not archived answers the document as it is without changing anything, so a repeat is safe. A document that was permanently deleted cannot be restored. A document_id is the stable identifier a document is listed under. Copy it exactly as listed; it cannot be guessed or built from a title or filename, and an id that is not the caller's own is treated as unknown. A change to one document passes expected_version, the version from the last read of that document, so it never overwrites a change the agent has not seen. If the document has changed since, nothing is changed and the call is refused as RESOURCE_CONFLICT with the document's current version: read the document again, check that the change still makes sense, then repeat it with the version the new read gives. Never guess a version and never repeat a refused call unchanged. Changing the library needs the user's content write permission (mcp:content-write), which the user grants separately; without it the call is refused and the refusal names the permission. The document library is available only to accounts it is enabled for. For any other account every Content tool refuses with feature_disabled, which no retry changes, so tell the user the library is not on their account instead of trying again.
Inputs
document_idstringrequired- The identifier of one of the caller's archived documents, copied exactly as content__list_documents gives it.
expected_versionintegerrequired- The version of the archived document from the last time it was read with content__get_document or content__list_documents. A document that has changed since is not restored: the call is refused with the current version so the document can be read again.
eracontextmcp_content__tag_documentsPut one of the caller's own tags on some of their documents, live or archived, or take it off them, in one call.WriteContent Tag Documents
Put one of the caller's own tags on some of their documents, live or archived, or take it off them, in one call. Either every named document ends up in the requested state or none changes: a document that already carries the tag as the user's own (or does not carry it, when removing) is left as it is, and the answer lists the documents that actually changed, which is none when a repeat changes nothing. Assigning a tag the library detected on a document confirms it as the user's own, which changes that document. This tool never creates a tag: it works only with a tag the user already has. A tag key names one of the caller's own tags. Read the keys with transactions__manage_transaction_tags and its list_tags action; a key that is not one of the caller's own live tags is refused. A document carries at most 10 tags, so an assignment that would exceed that refuses the whole request. The tag applied is the user's own, so it is never mistaken for a tag the library detected, and it advances each changed document's version. A document_id is the stable identifier a document is listed under. Copy it exactly as listed; it cannot be guessed or built from a title or filename, and an id that is not the caller's own is treated as unknown. Changing the library needs the user's content write permission (mcp:content-write), which the user grants separately; without it the call is refused and the refusal names the permission. The document library is available only to accounts it is enabled for. For any other account every Content tool refuses with feature_disabled, which no retry changes, so tell the user the library is not on their account instead of trying again.
Inputs
document_idsarrayrequired- The documents to change: 1 to 100 identifiers, each named once, copied exactly as content__list_documents gives them. If any one is not one of the caller's documents, live or archived, the whole request is refused and no document changes.
operationstringrequired- assign puts the tag on every named document; remove takes it off every named document.one of
assignremove tag_keystringrequired- The key of one of the caller's own tags, as transactions__manage_transaction_tags lists it with its list_tags action. A key that is not one of the caller's own live tags is refused; no tag is created.
eracontextmcp_content__tag_foldersPut one of the caller's own tags on some of their folders, or take it off them, in one call.WriteContent Tag Folders
Put one of the caller's own tags on some of their folders, or take it off them, in one call. Either every named folder ends up in the requested state or none changes: a folder that already carries the tag (or does not carry it, when removing) is left as it is, and the answer lists the paths of the folders that actually changed, which is none when a repeat changes nothing. A folder's tags belong to the folder: tagging a folder never tags the documents filed in it, and a document is never found by a tag its folder carries, so to tag documents use content__tag_documents. This tool never creates a tag: it works only with a tag the user already has. A tag key names one of the caller's own tags. Read the keys with transactions__manage_transaction_tags and its list_tags action; a key that is not one of the caller's own live tags is refused. A folder carries at most 10 tags, so an assignment that would exceed that refuses the whole request. Each changed folder's version advances. Read folder paths and the tags they carry with content__list_folders. A folder is written as a slash-separated path such as 'Taxes/2025', and paths are case-sensitive. Changing the library needs the user's content write permission (mcp:content-write), which the user grants separately; without it the call is refused and the refusal names the permission. The document library is available only to accounts it is enabled for. For any other account every Content tool refuses with feature_disabled, which no retry changes, so tell the user the library is not on their account instead of trying again.
Inputs
operationstringrequired- assign puts the tag on every named folder; remove takes it off every named folder.one of
assignremove pathsarrayrequired- The folders to change: 1 to 100 paths, each named once, copied exactly as content__list_folders gives them. If any one is not one of the caller's folders, the whole request is refused and no folder changes.
tag_keystringrequired- The key of one of the caller's own tags, as transactions__manage_transaction_tags lists it with its list_tags action. A key that is not one of the caller's own live tags is refused; no tag is created.
eracontextmcp_content__update_documentRename one of the caller's own documents, live or archived, move it to another folder, or both, and return the document as it stands afterwards.WriteContent Update Document
Rename one of the caller's own documents, live or archived, move it to another folder, or both, and return the document as it stands afterwards. Give title, folder_path or both, and at least one: a member left out keeps its current value, so a rename never changes the folder and a move never changes the title. An empty folder_path files the document at the top level. The document's tags are never changed by this tool. Read the folder paths with content__list_folders. A document_id is the stable identifier a document is listed under. Copy it exactly as listed; it cannot be guessed or built from a title or filename, and an id that is not the caller's own is treated as unknown. A change to one document passes expected_version, the version from the last read of that document, so it never overwrites a change the agent has not seen. If the document has changed since, nothing is changed and the call is refused as RESOURCE_CONFLICT with the document's current version: read the document again, check that the change still makes sense, then repeat it with the version the new read gives. Never guess a version and never repeat a refused call unchanged. A folder is written as a slash-separated path such as 'Taxes/2025', and paths are case-sensitive. Changing the library needs the user's content write permission (mcp:content-write), which the user grants separately; without it the call is refused and the refusal names the permission. The document library is available only to accounts it is enabled for. For any other account every Content tool refuses with feature_disabled, which no retry changes, so tell the user the library is not on their account instead of trying again.
Inputs
document_idstringrequired- The identifier of one of the caller's documents, live or archived, copied exactly as content__list_documents gives it.
expected_versionintegerrequired- The version of the document from the last time it was read with content__get_document or content__list_documents. A document that has changed since is not changed: the call is refused with the current version so the document can be read again.
folder_pathstring- The folder to file the document in, for example 'Taxes/2025', at most 200 characters. Give an empty string to file it at the top level. Leave out to keep the current folder.
titlestring- The new title, 1 to 200 characters. Leave out to keep the current title.
eracontextmcp_content__upload_documentsGet the link that opens the upload dialog of the caller's document library, so the user can add documents from their own device.WriteContent Upload Documents
Get the link that opens the upload dialog of the caller's document library, so the user can add documents from their own device. This tool does not upload anything and cannot receive file contents: give the user the link and they choose the files in the dialog. The link carries no credential; it opens in the user's own signed-in session, after sign-in if needed, and a copy sent to someone else gives them nothing. Use it when the user wants to add, upload or import files into their library. The message in the answer is one sentence to relay to the user with the link. Check the room left first with content__get_library_usage, and read what the library holds afterwards with content__list_documents.
Inputs
reasonstring- Optional free-text note stating, in one short sentence, why you are calling this tool. It does not affect the result and is recorded only for diagnostics. This tool takes no other input: do not put data, filters, or parameters here, and omit it entirely if you have nothing to say. Do not include personal or financial details.
eracontextmcp_holdings__get_holding_position_timelineRetrieves the quantity/cost-basis history for a single holding position, as a cursor-paginated series of dated steps — never a point-in-time snapshot, and there is no as_of_date parameter.WriteHoldings Get Holding Position Timeline
Retrieves the quantity/cost-basis history for a single holding position, as a cursor-paginated series of dated steps — never a point-in-time snapshot, and there is no as_of_date parameter. Each step is one provider-reported change to the position, ordered by change_date (a UTC calendar date) then change_instant, so two changes on the same date are two distinct steps. A step's quantity is null when the provider did not report a share count for it, and 0 on the step that closed the position. Returns up to limit steps per call (default 50, max 100); when has_more is true, pass the returned next_cursor as the cursor argument to fetch the next page. Repeating this until has_more is false reconstructs the position's complete history. Steps carry quantity and cost-basis facts only, unless include_valuation is set: that is a cost choice, off by default, and values each step at its own quantity and the close of the last session on or before its change_date (a step dated today or later takes the latest price; a cash or money-market step is valued at face value), or states why it could not be valued. Get holding_key from a holding returned by holdings__list_holdings or holdings__list_holdings_by_group, or from a lot returned by holdings__list_holding_lots. An unknown, hidden or another user's holding_key returns the same empty page.
Inputs
holding_keystringrequired- The holding's key: the holding_key (unhl_…) of a holding returned by holdings__list_holdings or holdings__list_holdings_by_group, or of a lot from holdings__list_holding_lots. Matched exactly and case-sensitively; a key of another kind (a holding group's, a lot's or a timeline step's) matches no holding.
cursorstring- Pagination cursor from a prior call's next_cursor field. Omit for the first page.
include_valuationboolean- When true, each step carries a valuation: its own quantity at the close of the last session on or before its change_date (the latest price for a step dated today or later; face value for a cash or money-market step), the market value and the unrealized gain, or a status saying why the step could not be valued. Default false: no step is valued and no price lookup is made. Set true only when the position's value history is needed.default
false limitinteger- Maximum number of timeline steps to return per call. Default: 50. Maximum: 100.default
50
eracontextmcp_holdings__get_holding_value_seriesReturns the value of one holding, holding group or account group on each trading day of a window, one series per currency: the quantity held at the end of each session times that session's unadjusted daily close, summed over the members that share a currency.WriteHoldings Get Holding Value Series
Returns the value of one holding, holding group or account group on each trading day of a window, one series per currency: the quantity held at the end of each session times that session's unadjusted daily close, summed over the members that share a currency. Name the subject with scope and key: scope holding with a holding_key (unhl_…) from holdings__list_holdings or holdings__list_holdings_by_group, scope holding_group with a holding_group_key (uhlg_…) from holdings__list_holding_groups, or scope account_group with an account_group_key (uagr_…) from accounts__list_financial_accounts. An empty series list comes with empty_state_message, which names the next step. Name the window with range, or with from and to (inclusive yyyy-MM-dd dates spanning at most 14000 days); with neither, the window is one_year ending today (UTC). The response states the window, range, granularity and history_start_date it read. Granularity weekly (the default here) keeps the last daily point of each ISO week; ask for daily for every trading day. With one_day, five_days or one_month, send granularity daily to get every session. Each series is in one currency; report each series in its own currency. Each series sums its member_count members; when left_out_members is not empty, report each series as the value of those members and name the members left out beside it. A null value_amount means the value is unknown for that day; read absence for why. Absence and gap reasons: quantity_unknown, the position records give no quantity for that day (they start at history_start_date); no_close, the price source has no close for a held member that day; source_unavailable, the price source could not be read, so ask again; outside_entitlement, the market-data source's licence holds no closes for those dates, independent of the user's plan; not_covered, no configured price source holds closes for the instrument. Read coverage for how much of the window is known and for its runs of unknown days, each with retryable true when asking again can fill it. Coverage: complete, every point valued; partially_covered, some points valued; not_covered, none valued; pending, a held member's prices had not arrived when the read stopped waiting, so ask again shortly. A preliminary point uses a close from a session still forming; a null point's gap retryable says whether asking again can value it. Live accounts are valued by default; to value a paper or scenario account, name every mode to value in include_simulation_modes (for example ["live", "paper"]). included_simulation_modes echoes the modes valued and excluded_account_count counts the account groups left out. left_out_members lists the members of the valued account groups that are in no series, each with the reason it could not be valued, by the valuation statuses holdings__list_holdings reports. One call values at most 100 positions, closed ones included; for a larger account group, ask for one of its holding groups or holdings, and for a larger holding group, for its holdings.
Inputs
keystringrequired- The subject's key, of the kind scope names: for holding, the holding_key (unhl_…) of a row holdings__list_holdings or holdings__list_holdings_by_group returns; for holding_group, the holding_group_key (uhlg_…) of a row holdings__list_holding_groups returns; for account_group, the account_group_key (uagr_…) of an account accounts__list_financial_accounts returns. Matched exactly; send the scope that matches the key's prefix (unhl_ holding, uhlg_ holding_group, uagr_ account_group). An empty series list comes with empty_state_message, which names the next step.
scopestringrequired- What key names: holding for one holding, holding_group for the holdings of one security in one account, or account_group for every holding of one account.one of
holdingholding_groupaccount_group fromstring- The first date of the window, inclusive, as yyyy-MM-dd. Send it with to, or alone; omit it for the one_year window that ends on to. The window spans at most 14000 days. Format: yyyy-MM-dd.
granularitystring- Which daily points each series keeps: weekly (the default) keeps the last trading day of each ISO week, monthly the last trading day of each calendar month, and daily every trading day. Each kept point is a daily value, and coverage lists every run of unknown days in full whatever the granularity.default
weekly include_simulation_modesarray- The kinds of account to value: 'live' is real money, 'paper' is a broker's practice account and 'scenario' is a user's hypothetical. Send several to value more than one, for example ["live", "paper"]. Omit to value live accounts only (the default, ["live"]); a list names at least one mode. included_simulation_modes echoes the modes valued and excluded_account_count counts the account groups left out.
rangestring- A named window ending today (UTC): one_day and five_days are the last one and five trading sessions; one_month, three_months, six_months, one_year and five_years are calendar spans; year_to_date starts on 1 January; max starts at the first position change among the members of the accounts it values, at most 14000 days back. Send range alone, or from and to alone. With neither range nor dates, the window is one_year. With one_day, five_days or one_month, send granularity daily to get every session.
tostring- The last date of the window, inclusive, as yyyy-MM-dd, read as a UTC calendar date. Omit it for today; a later date reads as today. Format: yyyy-MM-dd.
eracontextmcp_holdings__get_holdings_summarySummarises the user's investment accounts for the whole portfolio, one connection or one account group: for each account, the balance reported for it, how much account detail Forge has received for it, its open positions and what they are worth per currency, with a rollup per connection and a total.WriteHoldings Get Holdings Summary
Summarises the user's investment accounts for the whole portfolio, one connection or one account group: for each account, the balance reported for it, how much account detail Forge has received for it, its open positions and what they are worth per currency, with a rollup per connection and a total. Name the subject with scope: portfolio with no key; connection with a connection_id from connections__list_connections or accounts__list_financial_accounts; or account_group with an account_group_key (uagr_…) from accounts__list_financial_accounts. An answer with no summarised account comes with empty_state_message, which says why none was summarised and, where there is a step to take, what it is. reception.level is how much account detail Forge has received for the account, from least to most: none, balance_only, positions, positions_with_cost_basis, full. It describes what was received, and says nothing about the account's accuracy, the connection's strength, the investments' quality or anyone's fault. Each of its four details (account_value, positions, cost_basis, tax_lots) is received, partial, not_received or not_applicable; a partial or not_received detail says nothing about why, so do not tell the user their institution withholds it. A not_received positions, cost_basis or tax_lots detail on an account whose positions.open_count is 0 means Forge holds no open position for it, which does not say the account holds nothing. not_applicable means the step does not apply: cost_basis and tax_lots are not_applicable when the account has open positions and every one is a cash equivalent. In status_counts, every status other than priced describes Forge's pricing coverage of a position, and the level never reads a status. quantity_unknown counts the positions Forge found a price for but received no quantity for, so they have no value. Any open position received with no quantity, whatever its status, makes the positions detail partial and holds the account at the positions level, so every quantity_unknown position does, through its missing quantity; a status never lowers the level by itself. In by_currency, valued_amount sums the market values of the valued_position_count positions that have one, among position_count; read is_complete before presenting it as the whole value. unrealized_gain_amount sums the gains of the gain_position_count valued positions whose gain and cost basis are both in that entry's currency, and gain_cost_basis_amount is their cost basis; it is the gain of all of valued_amount only when gain_position_count equals valued_position_count. reported_balance is the balance reported for the account, as the accounts read states it; a current_amount of 0 does not by itself show that a zero balance was reported, so do not tell the user the account is empty or worth nothing on that alone; do not add it to valued_amount, subtract one from the other or reconcile them. Do not add amounts of different currencies; report each currency on its own. Live accounts are summarised by default; to summarise a paper or scenario account, name every mode to summarise in include_simulation_modes (for example ["live", "paper"]). included_simulation_modes echoes the modes summarised. simulation_excluded_account_count counts the visible accounts in scope, of any type, outside those modes, and hidden_account_count the accounts in scope, of any type, hidden by the plan or by the user; both are counted and not read or graded, so this answer does not say whether any of them is an investment account. When either count is above zero, mention it beside the summary and say the totals leave those accounts out. other_account_count counts the visible accounts that are neither an investment account type nor hold an open position. covering_lots counts the lots covering the open positions by who entered them: provider, manual (the user), synthetic (derived by Forge from a position because no lot was reported, never a tax lot) and other. positions.tax_lot_position_count counts the open positions covered by at least one lot, every one of them provider- or user-entered and dated. computed_at is when this summary was computed, not when its data arrived: reported_balance.as_of is the instant the balance is stated as of, and valuation.oldest_last_trade_at and valuation.oldest_close_session_date are the oldest last trade and the oldest session close among the prices that valued a position. This summary covers only the accounts listed for the user by the accounts read, so an account that read does not list is in no count here; it says nothing about a connection's state or when it last synced. connections__list_connections states each connection's state. The positions themselves are listed by holdings__list_holdings. One call reads at most 500 open positions; a larger subject is refused, naming a narrower scope to ask for or, for one account group, the tool that lists its positions page by page.
Inputs
scopestringrequired- What the summary covers: portfolio for every account you can see in the simulation modes summarised (live only unless include_simulation_modes names others), connection for the accounts of one connection, or account_group for one account.one of
portfolioconnectionaccount_group include_simulation_modesarray- The kinds of account to summarise: 'live' is real money, 'paper' is a broker's practice account and 'scenario' is a user's hypothetical. Send several to summarise more than one, for example ["live", "paper"]. Omit to summarise live accounts only (the default, ["live"]); a list names at least one mode. included_simulation_modes echoes the modes summarised and simulation_excluded_account_count counts the accounts left out.
keystring- The subject's key, of the kind scope names: for connection, a connection_id connections__list_connections or accounts__list_financial_accounts returns; for account_group, the account_group_key (uagr_…) of an account accounts__list_financial_accounts returns. Omit it for portfolio: a key sent with portfolio is refused. Matched exactly. An answer with no summarised account comes with empty_state_message, which says why none was summarised and, where there is a step to take, what it is.
eracontextmcp_holdings__list_holding_groupsLists the authenticated user's holding groups — holdings of the same security grouped across providers within the same account group.WriteHoldings List Holding Groups
Lists the authenticated user's holding groups — holdings of the same security grouped across providers within the same account group. Each group carries its resolved security identity, its member count, and the quantity and cost-basis aggregates over its open member positions, and by default a valuation read when the list is requested (never stored): the market price, whether it is a last trade, a session close or face value, the market value and the unrealized gain, or a status saying why the group could not be valued. A group whose members are different securities has no resolved identifiers and is not valued. A price source outage never removes a group; it only leaves groups unvalued. Set include_valuation to false when only quantities and cost basis are needed: it skips the price lookup. Returns only the groups with at least one open member position by default; set include_closed to add the groups whose every member position is closed. Narrow the list to one account with account_group_key. Each group's holding_group_key (uhlg_…) is the one key to pass to holdings__list_holdings_by_group to see its member holdings, or to holdings__update_holding_group to override its security name/type; every holding returned by holdings__list_holdings carries the same value as its holding_group_key.
Inputs
account_group_keystring- Only the groups in this account: its account_group_key (uagr_…), exactly as accounts__list_financial_accounts returns it and as each group carries it. Omit for every account.
cursorstring- Pagination cursor for the next page. Omit for the first page.
include_closedboolean- When true, also returns the groups with no open member position — groups whose every member position the provider no longer reports. Such a group lists with no quantity or cost-basis aggregates. Default false: only the groups with at least one open member position.default
false include_valuationboolean- When true (the default), each group carries a valuation: the market price, whether it is a last trade, a session close or face value, the market value and the unrealized gain, or a status saying why the group could not be valued. Set false when only quantities and cost basis are needed; it skips the price lookup and no group carries a valuation.default
true limitinteger- Maximum number of holding groups to return per page. Default: 50. Maximum: 100.default
50
eracontextmcp_holdings__list_holding_lotsLists the lots of a single holding position, as the provider reports them: each lot's quantity, its reported per-share cost basis (the provider's purchase price, distinct from the holding row's derived average_cost_per_share), its cost basis, acquisition price, wash-sale and realized gain/loss figures, its acquisition date, method and holding period, and its provenance (lot_source).WriteHoldings List Holding Lots
Lists the lots of a single holding position, as the provider reports them: each lot's quantity, its reported per-share cost basis (the provider's purchase price, distinct from the holding row's derived average_cost_per_share), its cost basis, acquisition price, wash-sale and realized gain/loss figures, its acquisition date, method and holding period, and its provenance (lot_source). Each lot is returned as valid-time intervals: one interval per provider report that changed it, so a lot reported differently over time has several. By default only the intervals open now are returned (the provider's current report for each lot); set include_closed_intervals to also return the closed ones, the lots' history. Intervals are ordered oldest first by valid_as_of_instant. A lot whose lot_source is "synthetic" is one position-level lot the provider reports per sync, not a real tax lot: never present it as one. position_is_closed is the position's current state — true when the provider no longer reports the position, false while it is open, omitted when no position is visible — and never an interval's: a closed interval is lot history, not a closed position. Every lot carries the holding_key it was read by. An unknown, hidden or another user's holding_key returns the same empty page. Returns up to limit intervals per call (default 50, max 100); when has_more is true, pass the returned next_cursor as the cursor argument to fetch the next page. Each open interval also carries, by default, a valuation read when the lots are requested (never stored): the lot's held quantity at the market price, the market value and the unrealized gain against the lot's own cost basis, or a status saying why it could not be valued; closed intervals carry none. Set include_valuation to false when only the reported lot facts are needed: it skips the price lookup. Get holding_key from the holding_key of a holding returned by holdings__list_holdings or holdings__list_holdings_by_group; use holdings__get_holding_position_timeline for the position's aggregate quantity/cost-basis history.
Inputs
holding_keystringrequired- The holding's key — the holding_key (unhl_…) of a holding returned by holdings__list_holdings or holdings__list_holdings_by_group. Matched exactly and case-sensitively; a key of another kind (a holding group's, a lot's or a timeline step's) matches no holding.
cursorstring- Pagination cursor from a prior call's next_cursor field, made with the same holding_key and include_closed_intervals. Omit for the first page.
include_closed_intervalsboolean- When true, also returns every closed lot interval — each lot's past reports, the lots' history. Default false: only the intervals open now. This is not the list tools' include_closed: a closed interval is a lot's history, and a position the provider no longer reports is a closed position, which the response states once in position_is_closed. A closed position's intervals are all closed, so its lots are returned only with this set.default
false include_valuationboolean- When true (the default), each open lot interval carries a valuation: the market value of the lot's held quantity, the unrealized gain against the lot's own cost basis, or a status saying why it could not be valued. Closed intervals are never valued. Set false when only the reported lot facts are needed; it skips the price lookup and no interval carries a valuation.default
true limitinteger- Maximum number of lot intervals to return per call. Default: 50. Maximum: 100.default
50
eracontextmcp_holdings__list_holdingsLists the authenticated user's investment holdings (stocks, ETFs, bonds, crypto, equity compensation, and other securities), one row per position per account, each with its quantity and cost-basis facts and, by default, a valuation read when the list is requested (never stored): the market price and whether it is a last trade, a session close or face value, the market value and the unrealized gain, or a status saying why the row could not be valued.WriteHoldings List Holdings
Lists the authenticated user's investment holdings (stocks, ETFs, bonds, crypto, equity compensation, and other securities), one row per position per account, each with its quantity and cost-basis facts and, by default, a valuation read when the list is requested (never stored): the market price and whether it is a last trade, a session close or face value, the market value and the unrealized gain, or a status saying why the row could not be valued. A price source outage never removes a row; it only leaves rows unvalued. Set include_valuation to false when only quantities and cost basis are needed: it skips the price lookup. Returns the open positions by default; set include_closed to add the positions the provider no longer reports. Pass as_of_date to list only the positions held on that UTC calendar date, each with its quantity and cost basis on that date. Narrow the list with account_group_key, connection_id, forge_security_key, security_type or holding_key (combined with AND). For one position's detail, pass as holding_key the holding_key of a row this tool or holdings__list_holdings_by_group returned: the list narrows to that holding under the same rules, so a closed position comes back only with include_closed; the same holding_key addresses holdings__list_holding_lots and holdings__get_holding_position_timeline. Use holdings__list_holding_groups to see holdings grouped by security with their aggregate quantity and cost basis, holdings__list_holding_lots for one position's lots as the provider reported them (per-lot cost basis and purchase price), or holdings__get_holding_position_timeline for one position's full quantity/cost-basis history.
Inputs
account_group_keystring- Only the holdings in this account: its account_group_key (uagr_…), exactly as accounts__list_financial_accounts returns it and as each holding row carries it. Omit for every account.
as_of_datestring- Optional ISO 8601 date (yyyy-MM-dd), read as a UTC calendar date. When set, only the positions held on that date are returned (at least one lot covered it), each with its quantity and cost basis at the end of the date; add include_closed to also return the positions closed on or before it. A position first held after the date is never returned. Identifiers, group membership and is_tombstone are the position's current values, not historical ones. When omitted, returns the current view. Format: yyyy-MM-dd.
connection_idstring- Only the holdings from this connection: a connection_id as connections__list_connections returns it, or a holding row's connection_id. Omit for every connection.
cursorstring- Pagination cursor for the next page. Omit for the first page.
forge_security_keystring- Only the holdings of this security, across every account: a holding row's forge_security_key, matched exactly. To answer "all my X across accounts", list once, then pass the forge_security_key of an X row here. One security can briefly carry more than one key until its identifiers converge across providers. Omit for every security.
holding_keystring- Only this one holding. The holding's key: the holding_key (unhl_…) of a row returned by holdings__list_holdings or holdings__list_holdings_by_group, matched exactly. Returns just that holding — use it for a single position's detail, then pass the same holding_key to holdings__list_holding_lots for its lots and to holdings__get_holding_position_timeline for its history. It narrows the ordinary list and keeps its rules: a closed position is returned only with include_closed, and with as_of_date only when the position qualifies on that date. A holding group's key, a lot's key or a timeline step's key matches no holding. Omit for every holding.
include_closedboolean- When true, also returns closed positions, each with quantity 0: on the current view, the positions the provider no longer reports (is_tombstone true); with as_of_date, the positions closed on or before that date. Default false: only open positions, or with as_of_date only the positions held on that date.default
false include_valuationboolean- When true (the default), each row carries a valuation: the market price, whether it is a last trade, a session close or face value, the market value and the unrealized gain, or a status saying why the row could not be valued. Set false when only quantities and cost basis are needed; it skips the price lookup and no row carries a valuation.default
true limitinteger- Maximum number of holdings to return per page. Default: 50. Maximum: 100.default
50 security_typestring- Only the holdings whose effective security type (the user's override, otherwise the provider's) is this type. Takes the same values as holdings__update_holding_group's security_type. Omit for every type.
eracontextmcp_holdings__list_holdings_by_groupLists the holdings belonging to a specific holding group (holdings of the same security grouped across providers), each with its quantity and cost-basis facts and, by default, a valuation read when the list is requested (never stored): the market price, whether it is a last trade, a session close or face value, the market value and the unrealized gain, or a status saying why the row could not be valued.WriteHoldings List Holdings By Group
Lists the holdings belonging to a specific holding group (holdings of the same security grouped across providers), each with its quantity and cost-basis facts and, by default, a valuation read when the list is requested (never stored): the market price, whether it is a last trade, a session close or face value, the market value and the unrealized gain, or a status saying why the row could not be valued. With as_of_date the valuation uses the close of the last session on or before that date, at the quantity held on it; a cash or money-market row is valued at face value whatever the date. A price source outage never removes a row; it only leaves rows unvalued. Set include_valuation to false when only quantities and cost basis are needed: it skips the price lookup. Returns the group's open positions by default; set include_closed to add the positions the provider no longer reports. Pass as_of_date to list only the group's positions held on that UTC calendar date, with their quantities on that date — group membership is always evaluated at current (query-time) state even when as_of_date is set, so an as-of result's membership must not be narrated as historical, only its quantities. Get the holding_group_key (uhlg_…) from holdings__list_holding_groups or from the holding_group_key field of any holding returned by holdings__list_holdings or holdings__list_holdings_by_group. An unknown or malformed key, another kind of key, or the key of a group not yet materialised for a newly synced holding returns an empty result, never an error.
Inputs
holding_group_keystringrequired- The group's key (uhlg_…): the holding_group_key of a group returned by holdings__list_holding_groups, or of any holding returned by holdings__list_holdings or holdings__list_holdings_by_group. A group row can lag a newly synced holding by one cascade hop; until it lands, this returns an empty result for its key.
as_of_datestring- Optional ISO 8601 date (yyyy-MM-dd), read as a UTC calendar date. When set, only the group's positions held on that date are returned (at least one lot covered it), each with its quantity and cost basis at the end of the date; add include_closed to also return the group's positions closed on or before it. A position first held after the date is never returned. Identifiers, group membership and is_tombstone are current, not historical; only quantities and cost bases are for the date. Format: yyyy-MM-dd.
cursorstring- Pagination cursor for the next page. Omit for the first page.
include_closedboolean- When true, also returns the group's closed positions, each with quantity 0: on the current view, the positions the provider no longer reports (is_tombstone true); with as_of_date, the positions closed on or before that date. Default false: only open positions, or with as_of_date only the positions held on that date.default
false include_valuationboolean- When true (the default), each holding carries a valuation: the market price, whether it is a last trade, a session close or face value, the market value and the unrealized gain, or a status saying why the row could not be valued. Set false when only quantities and cost basis are needed; it skips the price lookup and no holding carries a valuation.default
true limitinteger- Maximum number of holdings to return per page. Default: 50. Maximum: 100.default
50
eracontextmcp_holdings__update_holding_groupSets or clears the user-supplied security-name and/or security-type override for a holding group.WriteHoldings Update Holding Group
Sets or clears the user-supplied security-name and/or security-type override for a holding group. Applies identically regardless of which provider the underlying holdings came from — there is no provider-specific behavior. At most one of security_name or clear_security_name may be supplied; independently, at most one of security_type or clear_security_type may be supplied. At least one of the four fields must be supplied. Get the holding_group_key (uhlg_…) from holdings__list_holding_groups, or from the holding_group_key field of any holding returned by holdings__list_holdings or holdings__list_holdings_by_group.
Inputs
holding_group_keystringrequired- The group's key (uhlg_…): the holding_group_key of a group returned by holdings__list_holding_groups, or of any holding returned by holdings__list_holdings or holdings__list_holdings_by_group. An unknown or malformed key, or another kind of key, returns a clean not-found result, never an exception.
clear_security_nameboolean- When true, reverts the effective security name to the provider-supplied value. Mutually exclusive with security_name.
clear_security_typeboolean- When true, reverts the effective security type to the provider-supplied value. Mutually exclusive with security_type.
security_namestring- The user-supplied security name override, up to 200 characters. Mutually exclusive with clear_security_name.
security_typestring- The user-supplied security type override. It takes precedence over the provider-supplied value or, when no provider value was ever synced, the value derived from the group's members. Mutually exclusive with clear_security_type.
eracontextmcp_insights__get_cash_flow_summarySummarize one period's cash flow: total income, total expense and net, with the categories behind each side, largest first.WriteInsights Get Cash Flow Summary
Summarize one period's cash flow: total income, total expense and net, with the categories behind each side, largest first. Use it for questions like 'where did my money go this month?' or 'what came in and what went out?'. income.total and expense.total sum every category on that side, before top_n removes any, so a side's categories need not add up to its total; the difference is the categories the cut left out. net is income.total less expense.total. Every amount carries its own currency_code, and categories are formed per currency as well as per category: a vault holding two currencies returns the same category once per currency. The largest-first ranking runs within each currency, and top_n takes every currency's largest category before any currency's second, so a mixed list interleaves the currencies by rank. percent_of_total is a share of its side's total in that category's OWN currency, summed before the cut, so a side's percentages need not reach 100. A total or net whose currency_code is 'Multi' sums more than one currency, so it is a sum of magnitudes, not an amount of money: report the categories instead. 'Unknown' means no currency could be determined. Never state a currency the response did not give you. Each category carries display_order, its place in the person's own category list (0 first, each category followed by its own subcategories): sort ascending by it to list categories in the order the person keeps them. It is omitted for uncategorized money, for a category the person's list does not hold, and on every category when the list could not be read for this call. Both rows of a category spent in two currencies carry the same value. Send window instead of period to count a span back from the person's own today in their time zone; period.window and period.time_zone then name the window and the zone. period.start is omitted when the period has no lower bound ('all_time' as a period or a window, or a custom range starting 0001-01-01). The summary is empty only when both sides have no category; one side with no category beside a populated other side carries no envelope, and means nothing was counted on that side in the period, not that no money moved: only posted money classified as income or expense is counted, and transactions tagged as transfers, hidden transactions and transactions on hidden accounts are left out. Results include only posted/settled transactions; pending (authorization-hold) transactions are excluded. When a result — or a section of it — is empty, the response carries an empty_state envelope (kind, reason, next_step; multi-section responses instead use section-scoped variants such as accounts_empty_state) giving the authoritative reason it is empty and the recovery action. Read that envelope for the reason rather than inferring one — do not assume data is still syncing or settling. The response may also carry a top-level warnings array flagging data-health caveats (e.g. a connection to reconnect, or an unconfirmed check to retry); relay those caveats too. Session context from knowledge__get_financial_context_and_overview enriches these results with the user's profile, goals, and preferences.
Inputs
account_group_keystring- Filter to a specific account. Pass the account group projection key from accounts__list_financial_accounts (the account_group_key field). Omit to summarize every account.
include_subcategoriesboolean- When true, each category is a parent category carrying its subcategories, and top_n counts parent categories. Default false.default
false periodstring- Time range for the summary. Use 'custom' with both period_start and period_end for a specific date range.default
this_month period_endstring- Last date of a custom range (YYYY-MM-DD), on or after period_start. Required when period is 'custom'. Format: yyyy-MM-dd.
period_startstring- First date of a custom range (YYYY-MM-DD). Required when period is 'custom' or period_end is sent; sending it selects a custom range whatever the period, ending today when period_end is omitted. Format: yyyy-MM-dd.
top_ninteger- Number of categories to return on each side, income and expense: the largest by amount, ranked within each currency when the vault holds more than one. Default 10.default
10 windowstring- A span of dates counted back from the person's own today, in their time zone, instead of a period: last_7_days, last_30_days and last_90_days are the 7, 30 and 90 dates ending today, week_to_date runs from the Monday on or before today through today, month_to_date runs from the first of this month through today, last_month is the whole previous month, and all_time has no lower bound. A window's dates can differ from the period of the same name, which counts on the UTC date (period last_7_days spans 8 dates; period this_week starts on Sunday), so report period.start and period.end. Send it instead of period, period_start and period_end; sending it with any of them is refused. The response names the window and the time zone that decided today in period.window and period.time_zone.
eracontextmcp_insights__get_spending_by_periodShow how the person's own spending went, period by period: a grid of spending by category over one window, split into calendar months or 30-day blocks, one group per currency.WriteInsights Get Spending By Period
Show how the person's own spending went, period by period: a grid of spending by category over one window, split into calendar months or 30-day blocks, one group per currency. Use it for questions like 'how has my spending changed month to month?' or 'which categories grew over the last 90 days?'. For one period's income and expense use insights__get_cash_flow_summary; for one month day by day use insights__get_daily_category_spending. With nothing sent it reads last_90_days by month. periods lists the periods, earliest first, each with an inclusive start and end date; the first and last are cut at the window's ends, so a period can be shorter than a month or 30 days, and its dates say so. Every by_period and period_totals list holds one entry per period, in the same order. Each currency group lists its categories, each with its subcategories. A category's amounts include its subcategories', so add up categories, never a category and its subcategories; a group's total and period_totals are the sum of its categories. Amounts are spending, never negative. A period whose transaction_count is 0 holds no counted spending, which is not proof that nothing was spent: dates before an account's imported history begins, or before it was connected, also read 0. Do not report a period of 0 as no spending, or a rise from it as growth, unless the person's history is known to cover it. Every amount carries its own currency_code, and nothing is summed across currencies: report each currency group on its own. 'Unknown' means no currency could be determined; never add it to or compare it with another currency. Never state a currency the response did not give you. The window is counted back from the person's own today in their time zone, which window.time_zone names. window.start is omitted for all_time, whose first period holds the person's earliest spending: by month it starts on the first of that month, by block30 on the first date of the 30-day block that holds it, so it can start before the earliest spending. all_time with no spending has no periods. The whole window is read at once: an order is left out when every charge that settled it is inside the window, so a month here can differ from insights__get_daily_category_spending's answer for that month, which reads the month alone. row_limit_reached true means the grid is incomplete: it holds only the window's earliest spending, so say so and ask again with a shorter window. is_backfilling true means a connection is still importing its history, so spending may be missing. Only expenses are counted: income, pending transactions, transactions tagged as transfers and transactions on hidden accounts are left out. Results include only posted/settled transactions; pending (authorization-hold) transactions are excluded. When a result — or a section of it — is empty, the response carries an empty_state envelope (kind, reason, next_step; multi-section responses instead use section-scoped variants such as accounts_empty_state) giving the authoritative reason it is empty and the recovery action. Read that envelope for the reason rather than inferring one — do not assume data is still syncing or settling. The response may also carry a top-level warnings array flagging data-health caveats (e.g. a connection to reconnect, or an unconfirmed check to retry); relay those caveats too. Session context from knowledge__get_financial_context_and_overview enriches these results with the user's profile, goals, and preferences.
Inputs
bucketstring- The kind of period to split the window into: month for calendar months, block30 for blocks of 30 days counted back from the window's end, so every block but the earliest holds 30 days. The window's end is the person's today for every window but last_month, which ends on the last date of the previous month. Omitted, it is month.
windowstring- The span of dates to read, counted back from the person's own today in their time zone: last_7_days, last_30_days and last_90_days are the 7, 30 and 90 dates ending today, week_to_date runs from the Monday on or before today through today, month_to_date from the first of this month through today, last_month is the whole previous month, and all_time has no lower bound. Omitted, it is last_90_days. The response names the window, its dates and the time zone that decided today in window.
eracontextmcp_knowledge__confirm_or_reject_inferenceAccept or dispute an AI-inferred financial fact.WriteKnowledge Confirm Or Reject Inference
Accept or dispute an AI-inferred financial fact. When rejecting, optionally provide the user's correct value.
Inputs
actionstringrequired- Required. 'confirm' when the person agrees with the value, 'reject' when they do not.one of
confirmreject slugstringrequired- Required. The slug of the fact to confirm or reject, copied from the fact as knowledge__get_financial_context_and_overview served it.
corrected_valuestring- Optional; absent means the verdict states no value of its own. The person's own value for the fact, in their words, as one typed answer whose answer_type is the one the fact was served with. It replaces a value someone stands behind only with action 'reject'.
qualifier_keystring- Optional; absent means the record with no period, place or kind. Send the qualifier_key of the record to act on, copied unchanged from the record as knowledge__recall_history or knowledge__get_financial_context_and_overview served it, or from the records a not-found answer lists; never write one.
recordstring- Optional; absent means the fact's general record. Send kind 'instance' with the instance_id a read served when the entry carries one, or kind 'general' for the record that belongs to no particular thing.
eracontextmcp_knowledge__defer_questionSkip a question permanently or snooze it to resurface after a specified number of days.WriteKnowledge Defer Question
Skip a question permanently or snooze it to resurface after a specified number of days.
Inputs
actionstringrequired- The action to take: 'skip' to decline the question, or 'snooze' to defer it for a number of days.one of
skipsnooze question_slugstringrequired- The slug of the question to skip or snooze. Get available slugs from knowledge__get_pending_questions.
pack_slugstring- The question pack slug containing this question. Defaults to 'financial-profile-v1' if omitted.
snooze_daysinteger- Number of days to snooze the question (required when action is 'snooze'). The question will be re-surfaced after this many days.
eracontextmcp_knowledge__rememberStore a financial fact, preference, or goal.WriteKnowledge Remember
Store a financial fact, preference, or goal. Populate exactly one typed value field matching the answer_type (text, number, money, date, or boolean).
- Idempotent
Inputs
answerstringrequired- Required. The person's answer; its answer_type names the shape and each shape carries only its own members.
slugstringrequired- Required. The standalone umbrella machine-readable name of the property this fact records: what kind of fact it is. Exclude qualifiers that are represented by other fields, and use lowercase words joined by hyphens (kebab-case). For prompted questions, use the question's slug as knowledge__get_pending_questions served it.
as_ofstring- Optional; absent means the day of the write, and a later day is taken as the day of the write. The day the figure was true or known, as YYYY-MM-DD: the date of the statement it comes from, or the day the person says it held. Format: yyyy-MM-dd.
categorystring- Optional; absent means 'preferences'. The group the fact is filed under: the category knowledge__get_pending_questions served with the question, or the closest one for a fact the person mentioned.default
preferences confidencestring- Optional; absent means 'definitive', except for a fact only the person can settle, where you send it. Send 'definitive' when the person stated the fact. For a fact only the person can settle, 'definitive' and 'confirmed' go only with source 'prompted' or 'conversational'. How certain the fact is: 'definitive' (the person stated it), 'confirmed' (inferred and the person confirmed it), 'inferred' (you derived it, not yet confirmed) or 'observed' (computed from data).
coverageobject- Optional; absent means the figure covers no stated period. Send it whenever the person names the period the figure is for: a tax year, a year, a month or a day. The periods come from the person's words.
display_mask_typestring- Optional. When absent and the answer_type admits a mask, the record keeps the mask it holds, else takes one from a record it replaces or from its fact, else has none; an answer of any other answer_type stores none. Send it whenever the value is an identifier the person would not want shown in full, naming the kind of identifier it is: 'ssn' for a US Social Security number, 'national_id_number' for any other national identity number, such as a UK National Insurance number, a Canadian SIN or an EU national ID, 'tax_id' for an EIN, an ITIN or a UK UTR, 'bank_routing_number' for a routing number, sort code or transit number, 'account_number' for the number of an account with a bank or any other provider, such as a utility, or an IBAN, 'card_number' for a payment card number, 'passport_number' for a passport number and 'driver_license_number' for a driver's licence number. The kind comes from what the identifier is, not from how the person typed it. Send the identifier itself as the answer's value; it is stored and served as given, and this member only records what kind of identifier it is. It goes with an answer_type of 'text', 'text-multiline', 'number', 'scale', 'money', 'money-periodic' or 'money-relative'; any other answer_type is refused.
jurisdictionobject- Optional; absent means the figure holds for no stated place. Send it whenever the person names the country or region the figure is for. The place comes from the person's words.
kindstring- Optional; absent means 'actual'. How the person put the figure: 'actual' for what happened or holds, 'estimate' for a figure they worked out or guessed, 'aspirational' for one they hope to reach.default
actual pack_slugstring- Optional; absent means 'financial-profile-v1'. The question pack's slug as knowledge__get_pending_questions served it, when the answer is to one of its questions.
qualitiesobject- Optional; absent means the person did not say whether the figure is final or exact. Status applies to an actual figure that totals its periods, where it is required; exactness applies to an actual figure only. Both come from the person's words.
recordstring- Optional; absent means the fact's general record. Required for a fact the person holds one thing at a time, such as a second card. Send kind 'instance' with the instance_id a read served to write a record the person already holds, kind 'new' with a request_id you mint to create a thing they now hold, or kind 'general' for the record that belongs to no particular thing.
replacesarray- Optional; absent means the write replaces no other record. List the qualifier_key of each record this figure restates, copied unchanged from the record as knowledge__recall_history or knowledge__get_financial_context_and_overview served it; never write one. Name each record once, never the record this write writes, and send none with a compound answer.
sourcestring- Optional; absent means 'conversational'. How you learned the fact: 'prompted' (the person answered a question), 'conversational' (they mentioned it in chat), 'inferred' (you derived it), 'observed' (computed from data) or 'imported' (from an external source).default
conversational tagsarray- Optional; absent means no tags. Short labels you choose, such as 'tax-relevant'.
valid_untilstring- Optional; absent means no earlier re-check. Applies to an actual figure only; an estimate or a goal ignores it. A date after today, as YYYY-MM-DD, that the person gave as the day to check the fact with them again. Format: yyyy-MM-dd.
eracontextmcp_nurture__set_subscriptionSubscribe the caller to, or unsubscribe them from, a nurture (lifecycle email) campaign.WriteNurture Set Subscription
Subscribe the caller to, or unsubscribe them from, a nurture (lifecycle email) campaign. Takes effect immediately — no confirmation step, and always reversible by calling this tool again with the opposite value. Unsubscribing from a campaign the caller was never enrolled in is a safe no-op. Call nurture__get_my_status first to see the caller's current campaigns and subscription state.
- Idempotent
Inputs
campaign_idstringrequired- The campaign identifier. Obtain from nurture__get_my_status's response.
subscribedbooleanrequired- Set to true to subscribe (resubscribe if previously unsubscribed) or false to unsubscribe.
eracontextmcp_referral__join_referral_programEnroll the user in the referral program and create their affiliate profile.WriteReferral Join Referral Program
Enroll the user in the referral program and create their affiliate profile.
- Idempotent
Inputs
reasonstring- Optional free-text note stating, in one short sentence, why you are calling this tool. It does not affect the result and is recorded only for diagnostics. This tool takes no other input: do not put data, filters, or parameters here, and omit it entirely if you have nothing to say. Do not include personal or financial details.
eracontextmcp_referral__switch_referral_campaignSwitch the user's active referral campaign to a different slug.WriteReferral Switch Referral Campaign
Switch the user's active referral campaign to a different slug.
- Idempotent
Inputs
slugstringrequired- The campaign slug to switch to. Valid values: 'invite' or 'creator'.
eracontextmcp_transactions__import_csv_transactionsImport transactions from a CSV export of Monarch, Copilot, YNAB, Mint, or Wells Fargo.WriteTransactions Import Csv Transactions
Import transactions from a CSV export of Monarch, Copilot, YNAB, Mint, or Wells Fargo. Use preview_only=true to validate before committing.
- Idempotent
Inputs
account_group_keystringrequired- The account group projection key of the manual account to import into. Obtain from accounts__list_financial_accounts (the account_id field). Must be a manual account.
csv_contentstringrequired- The complete CSV text content (including header row). Pass the raw CSV as a string — do NOT base64-encode, MCP is text-native.
formatstring- Optional format hint to bypass auto-detection. Supported values: "monarch", "copilot", "ynab", "mint", "wellsfargo", "chase", "bankofamerica", "amex", "schwab". If omitted, format is auto-detected from the CSV header row.
preview_onlyboolean- When true, parse and validate the CSV but do not write transactions. Returns per-row validation verdicts (valid/invalid + reason). Default: false.
eracontextmcp_transactions__manage_automation_rulesCreate, list, update, delete, or enable rules that auto-categorize or tag matching transactions.WriteTransactions Manage Automation Rules
Create, list, update, delete, or enable rules that auto-categorize or tag matching transactions. Supports per-transaction and pattern-detection (transfer/recurring) rules.
Inputs
actionstringrequired- What to do. Create adds a new rule, list shows existing rules, update changes a rule's conditions or actions, delete removes a rule permanently, enable/disable turns a rule on or off without deleting it, preview tests filters against recent transactions without saving anything.one of
createlistupdatedeleteenabledisablepreview actionsarray- What to do with matching transactions (required for create and update). You can combine multiple actions. For category, merchant rename, description, review status, hide, and transfer actions, only the highest-priority rule's action applies. Tag actions (add/remove) always apply from all matching rules.
application_scopestring- Determines which transactions this rule applies to. Prospective applies only to new transactions going forward. Retroactive applies only when explicitly re-running against existing transactions. Both (default) does both.
applies_fromstring- Only apply this rule to transactions dated on or after this date (YYYY-MM-DD). Omit to apply to transactions of any date. Format: yyyy-MM-dd.
applies_tostring- Only apply this rule to transactions dated on or before this date (YYYY-MM-DD). Omit to apply to transactions of any date. Format: yyyy-MM-dd.
apply_retroactivelyboolean- Whether to apply the rule to the user's existing transactions. Default: true — matching transactions are updated in the background after the rule is saved, and the response reports retroactive_status in_progress until that finishes. When updating an existing rule, the old matches are undone first and the new definition is applied fresh, both in the background. Set to false only if the user explicitly asks for the rule to apply to future transactions only; existing transactions are then left as they are.
descriptionstring- An optional note explaining what this rule does or why it was created.
filtersarray- Conditions that determine which transactions this rule matches (required for create and update). When multiple filters are provided at the top level, ALL must match (AND logic). Use 'or' type filters to match ANY of several conditions.
groupstring- The themed group to file a custom rule under on create or update: 'spending_habits' (how often or where the user spends), 'problems_and_anomalies' (errors, fees, and unusual activity), 'income_and_transfers' (pay, deposits, refunds, and money movement), 'subscriptions_and_recurring' (recurring charges and price changes), or 'tax_and_record_keeping' (labelling transactions for taxes and records). Omit it to leave the rule ungrouped, shown under custom rules. Update replaces the rule's whole definition, so on update omitting group CLEARS any group the rule already has — pass the rule's current group (the 'group' field from the transactions__manage_automation_rules list action) to keep it. Library rules keep the group their definition assigns: omit group or pass its current value when updating one. 'category_mapping' is reserved for rules generated automatically by custom-category setup and is rejected.
include_inactiveboolean- When listing rules, set to true to also include disabled rules. Default: false (only active rules are shown).
pattern_specstring- The pattern detection specification. Required for pattern-scope rules. Supports four types: pair_match (transfer detection between accounts), frequency_threshold (counting occurrences in a window), recurring_group (periodic merchant charge detection), and statistical_anomaly (z-score anomaly detection).
priorityinteger- Rules with higher priority numbers are evaluated first. When two rules could both set a category (or merchant name, etc.) on the same transaction, the higher-priority rule wins. Default: 0.
revert_retroactivelyboolean- When deleting or disabling a rule, whether to undo the changes it previously made to transactions (e.g., remove the category it assigned, remove tags it added). Default: false — previous changes are left in place. Set to true for a clean undo so the user's transactions return to their state before the rule existed; the undo runs in the background after the rule is deleted or disabled, and the response reports retroactive_status in_progress until it finishes.
rule_keystring- The unique key of an existing rule. Required for update, delete, enable, and disable. Get this from the 'list' action response.
rule_namestring- A short, descriptive name for the rule (e.g., 'Categorize Uber as Transportation'). Required for create and update.
rule_scopestring- The rule scope: 'transaction' (default) evaluates filters against each individual transaction. 'pattern' evaluates a pattern specification against a time-windowed batch of transactions.
trigger_modestring- When to trigger pattern evaluation. Defaults to 'on_batch_complete' for pattern rules, 'on_each_transaction' for transaction rules.
user_overridesstring- Optional overrides for library rule parameters. Must match the rule's pattern_spec type (e.g. pair_match overrides for a pair_match rule). Library rules cannot be created or deleted, but their behavior can be customized using this field on update.
versioninteger- The current version number of the rule, used to prevent conflicting edits. REQUIRED for update, delete, enable, and disable. Get this value from the 'list' action response. If someone else changed the rule since you last read it, the operation will fail with a conflict error — re-read the rule and retry.
window_daysinteger- How many days to look back when searching for matching patterns. Required for pattern-scope rules. Must be between 1 and 365.
window_exclude_trigger_accountboolean- When true, transactions from the same account as the trigger are excluded from the window query. Useful for transfer detection to avoid self-matching.
window_lookahead_daysinteger- How many days to look ahead when searching for matching patterns. Default: 0 (no lookahead).
eracontextmcp_transactions__manage_categoriesCreate, update, hide, delete, merge, or reorder spending categories.WriteTransactions Manage Categories
Create, update, hide, delete, merge, or reorder spending categories. New categories require a parent_category_key and URL-safe slug.
Inputs
actionstringrequired- What to do. Create adds a new custom category, update changes display properties, hide/unhide controls visibility, delete removes a user-created category, merge_categories combines multiple into one.one of
createupdatehideunhidedeletemerge_categoriesreorderreset apply_retroactivelyboolean- When true, re-evaluates transactions (up to 12 months) in the background after mapping rules are created; the response reports retroactive_status in_progress until that finishes. Defaults to true.
assignment_eligibilitystring- Controls whether the AI agent can auto-assign transactions to this category. Optional.
category_keystring- The category key to operate on. Required for update, hide, unhide, delete. For merge_categories this is the target category key.
descriptionstring- A description of what this category covers. Optional.
display_orderinteger- Display order within sibling group. Optional.
icon_namestring- A single UTF emoji character used as the category icon in the UI (e.g. "🏠", "💰"). Optional.
merge_source_keysarray- Category keys to merge into the target. Required for merge_categories. These categories will be hidden.
namestring- The display name for the category. Required for create, optional for update (null = unchanged).
parent_category_keystring- The parent category key (fcat_*) under which to create the new category. Required for create.
reorder_entriesarray- List of {category_key, display_order} pairs. Required for reorder.
slugstring- A unique URL-safe slug for the new category (lowercase alphanumeric and hyphens, 2-50 chars). Required for create.
source_system_keysarray- System category keys (fcat_*) whose transactions should be routed to this new category. Used with create and merge_categories. Each source gets a mapping rule.
spending_typestring- Spending classification for budgeting and analytics. Optional.
eracontextmcp_transactions__manage_transfer_linksList, confirm, or reject system-detected transfer pairs between transactions (e.g.WriteTransactions Manage Transfer Links
List, confirm, or reject system-detected transfer pairs between transactions (e.g. a credit card payment matched to a bank debit).
Inputs
actionstringrequired- What to do: 'list' shows detected transfer links between accounts, 'confirm' marks a detected transfer as confirmed by the user (upgrades confidence), 'reject' removes a false positive transfer link and prevents re-detection.one of
listconfirmreject transaction_idstring- When listing, only show transfer links involving this specific transaction. Optional.
transfer_link_idstring- The unique identifier of the transfer link to confirm or reject. Get this from the 'list' action response. Required for confirm and reject.
eracontextmcp_transactions__update_transactionsBulk-update up to 100 transactions: set category, description, merchant name, or review status.WriteTransactions Update Transactions
Bulk-update up to 100 transactions: set category, description, merchant name, or review status. Use clear_* fields to revert overrides to automatic values.
- Idempotent
Inputs
transaction_idsarrayrequired- IDs of the transactions to update (up to 100 at once). Get these from transactions__list_transactions or transactions__search_transactions.
category_keystring- The category to assign to these transactions. Call transactions__list_spending_categories first to get valid category keys.
clear_categoryboolean- Remove the user's manual category choice, reverting to the automatically detected category.default
false clear_descriptionboolean- Remove the user's custom description, reverting to the original description from the bank.default
false clear_merchant_nameboolean- Remove the user's custom merchant name, reverting to the original name from the bank.default
false clear_review_statusboolean- Clear the review status. Use this instead of review_status when removing a status.default
false descriptionstring- Set a custom note or description for these transactions.
merchant_namestring- Set a custom merchant name for these transactions (e.g., rename 'AMZN*1234' to 'Amazon').
review_statusstring- Review status to assign: needs_review, reviewed, or flagged.
eracontextmcp_accounts__manage_accountCreate, update, delete, or set the balance of a manually tracked account.DestructiveAccounts Manage Account
Create, update, delete, or set the balance of a manually tracked account. Use action to specify the operation; amount must be a positive integer with a separate direction field.
Inputs
actionstringrequired- What to do: 'create' adds a new manual account, 'update' changes account properties (account_name applies to any account type; other fields are manual-only), 'delete' soft-deletes a manual account and its transactions, 'set_balance' records a balance snapshot on a manual account.one of
createupdatedeleteset_balance account_group_keystring- The account group projection key identifying the account. Required for update, delete, and set_balance. Obtain from accounts__list_financial_accounts (the account_id field).
account_namestring- The user-supplied display name (e.g., "Home Mortgage", "Savings Jar"). Required for create. On update, applies to any account type — manual or connected — and writes a user-layer override that surfaces as the effective name; the institution-supplied name is preserved underneath. Mutually exclusive with 'clear_account_name'.
account_number_maskstring- Partial account number (last 4 digits). Do NOT supply the full account number. On update: manual accounts only.
account_typestring- The account type classification. Required for create (manual). On update: manual accounts only — supplying this for a connected account is rejected.
amount_minor_unitsinteger- The balance amount in integer minor units (e.g., 150050 for $1,500.50, or 1000 for 1000 JPY). Required for set_balance. Positive = asset; negative = liability.
as_of_datestring- As-of for the balance record in ISO 8601 format. Omit it when the balance is current ("today", "now"): the balance is then dated at the moment it is recorded. Pass a date alone (e.g., "2026-04-15") for a past day the user names: it states the balance at the close of that UTC day. Include a time of day (e.g., "2026-04-15T09:30:00Z") only when the user names an exact moment. Optional, set_balance only.
balance_currencystring- ISO 4217 currency code Era supports (e.g. EUR), or one of: BTC, ETH, USDT, USDC, BNB, XRP, ADA, SOL, DOGE, SHIB. Required for set_balance.
clear_account_nameboolean- On update: set to true to remove a previously applied user account-name override, reverting the display name to the institution-supplied value (or empty when no provider name exists). Mutually exclusive with 'account_name'. Account-type-agnostic.
currencystring- ISO 4217 currency code Era supports (e.g. EUR), or one of: BTC, ETH, USDT, USDC, BNB, XRP, ADA, SOL, DOGE, SHIB. Required for create.
initial_balance_minor_unitsinteger- Starting balance in integer minor units (e.g., 150050 for $1,500.50, or 1000 for 1000 JPY). Positive = asset; negative = liability. Optional, create only.
institution_namestring- Institution name for display and fingerprint matching (e.g., "Chase", "Fidelity"). On update: manual accounts only.
simulation_modestring- Whether the account is real or simulated. Applies to create and update of manual accounts only; supplying it for a connected account is rejected because a connected account's mode comes from its provider. 'live' is real money, 'scenario' is a hypothetical the user is modelling, and 'paper' is a broker practice account the user tracks by hand. Omitted on create means 'live'; omitted on update leaves the mode unchanged.
eracontextmcp_accounts__set_account_archiveSet the user's archive choice on one of their financial accounts.DestructiveAccounts Set Account Archive
Set the user's archive choice on one of their financial accounts. intent='archive' archives the account, intent='keep' keeps it out of the archive even when its connection would archive it (a connection that has gone a long time without a successful sync, or that was disconnected), and intent='clear' removes the user's choice so the connection decides again. Any account the user holds takes the choice: manual, connected, or one whose connection they disconnected. Archiving is display only: it changes no sync, total, analysis or plan limit, and it does not hide the account. To hide an account from analytics use accounts__set_account_visibility instead. Repeating the choice already in force changes nothing and adds nothing to the user's history. The response states whether the account is now archived and why. Use accounts__list_financial_accounts (with include_severed=true for accounts of disconnected connections) to get the account_group_key and each account's current archive state.
Inputs
account_group_keystringrequired- The account group projection key. Obtain from accounts__list_financial_accounts (the account_group_key field).
intentstringrequired- 'archive' to archive the account whatever its connection says; 'keep' to keep it out of the archive whatever its connection says; 'clear' to remove the user's choice, so the account is archived exactly when its connection's archive rule archives it.one of
cleararchivekeep idempotency_keystring- Optional idempotency key, mirroring the REST Idempotency-Key header; it must not be blank. The key is validated but does not decide whether a request applies: the requested choice and the account's current archive choice do. A key is not required for safety: even without a key, a keyless retry of the same logical operation is deduplicated server-side via a deterministic write-side-derived event key, collapsing to a single effect, where the same logical operation means the same choice requested again with no other choice made on the account in between. A repeat of the choice already in force changes nothing, and two submissions of one choice made before either is applied apply it once, whatever key each carries. A retry made after another choice has replaced it (for example the user cleared it in the app) is a new operation and applies the choice again, with this key or any other, so when an earlier call's outcome is unknown, read the account's archive state with accounts__list_financial_accounts (with include_severed=true for an account of a disconnected connection) before retrying.
eracontextmcp_billing__cancel_subscriptionTwo-step cancellation: first call returns a confirmation key; second call with that key executes the cancellation.DestructiveBilling Cancel Subscription
Two-step cancellation: first call returns a confirmation key; second call with that key executes the cancellation.
Inputs
reasonstringrequired- Why the user wants to cancel. Summarize their stated reason concisely.
accept_offerboolean- Set to true to accept the retention discount offer. Set to false or omit to decline and receive the billing page URL for manual cancellation. Only used on the second call alongside confirmation_key.
billing_group_idstring- The billing group this call acts on. Omit it to act on the user's own billing group, which is what almost every call wants. To act on another group, pass one of the billing_group_id values listed in billing_group_contexts by billing__get_current_plan; only contexts with can_manage_billing true can be changed, and their invoices and offer previews read, while any member may list the subscriptions that cover them (a member's list omits the amounts the payer is charged and the offers open to the payer). A group the user does not belong to, or a value that is not a billing group id, is refused and the call never falls back to another group. When a flow takes more than one call (a confirmation key, or a preview then a confirm), pass the same billing_group_id on each.
confirmation_keystring- The confirmation key from the first call. Omit on first call to receive a retention offer; pass it on the second call along with accept_offer.
eracontextmcp_connections__disconnect_institutionPermanently remove a linked institution connection and unlink all associated accounts.DestructiveConnections Disconnect Institution
Permanently remove a linked institution connection and unlink all associated accounts. Get the connection_id from accounts__list_financial_accounts.
Inputs
connection_idstringrequired- The connection ID of the institution to disconnect. Obtain from accounts__list_financial_accounts (the connection_id field on account entries).
eracontextmcp_content__archive_documentArchive one of the caller's own documents.DestructiveContent Archive Document
Archive one of the caller's own documents. Archiving is the default way to remove a document. Archiving keeps the document, with its folder and tags, and leaves it out of every default listing; content__restore_document brings it back. Archiving also revokes every active share link to the document, and restoring does not bring those links back: content__create_share_link makes a new one. Removing a document for good is the separate content__delete_document_permanently tool, which only the user's explicit request justifies. Use this to remove a document the user no longer wants in view. It does not remove the document for good, and this tool cannot. The answer gives the instant the document was archived; archiving a document that is already archived answers the same instant without changing anything, so a repeat is safe. If the document was already deleted permanently, the answer says permanent is true with the instant it was deleted, and nothing is changed. An archived document is still read with its document_id and carries archived_at. A document_id is the stable identifier a document is listed under. Copy it exactly as listed; it cannot be guessed or built from a title or filename, and an id that is not the caller's own is treated as unknown. A change to one document passes expected_version, the version from the last read of that document, so it never overwrites a change the agent has not seen. If the document has changed since, nothing is changed and the call is refused as RESOURCE_CONFLICT with the document's current version: read the document again, check that the change still makes sense, then repeat it with the version the new read gives. Never guess a version and never repeat a refused call unchanged. Changing the library needs the user's content write permission (mcp:content-write), which the user grants separately; without it the call is refused and the refusal names the permission. The document library is available only to accounts it is enabled for. For any other account every Content tool refuses with feature_disabled, which no retry changes, so tell the user the library is not on their account instead of trying again.
Inputs
document_idstringrequired- The identifier of one of the caller's documents, copied exactly as content__list_documents gives it.
expected_versionintegerrequired- The version of the document from the last time it was read with content__get_document or content__list_documents. A document that has changed since is not archived: the call is refused with the current version so the document can be read again.
eracontextmcp_content__delete_document_permanentlyPermanently delete one of the caller's own documents.DestructiveContent Delete Document Permanently
Permanently delete one of the caller's own documents. This cannot be undone: the document and the facts the user has not confirmed from it are removed from the library, it can no longer be read or restored, and its size returns to the user's allowance. This is not a promise that no other record of it exists anywhere. Archiving with content__archive_document is the default. Archiving keeps the document, with its folder and tags, and leaves it out of every default listing; content__restore_document brings it back. Archiving also revokes every active share link to the document, and restoring does not bring those links back: content__create_share_link makes a new one. Use this tool only when the user has clearly asked to delete this document permanently, say so back to them, and set confirm to the exact text "permanently delete" only after they agree. A document still being extracted has that work cancelled first. The answer says permanent is true and when the document was deleted; repeating the call answers the same receipt without changing anything. A document_id is the stable identifier a document is listed under. Copy it exactly as listed; it cannot be guessed or built from a title or filename, and an id that is not the caller's own is treated as unknown. A change to one document passes expected_version, the version from the last read of that document, so it never overwrites a change the agent has not seen. If the document has changed since, nothing is changed and the call is refused as RESOURCE_CONFLICT with the document's current version: read the document again, check that the change still makes sense, then repeat it with the version the new read gives. Never guess a version and never repeat a refused call unchanged. Changing the library needs the user's content write permission (mcp:content-write), which the user grants separately; without it the call is refused and the refusal names the permission. The document library is available only to accounts it is enabled for. For any other account every Content tool refuses with feature_disabled, which no retry changes, so tell the user the library is not on their account instead of trying again.
Inputs
confirmstringrequired- Exactly "permanently delete". Set it only after the user has agreed to delete this document permanently.one of
permanently delete document_idstringrequired- The identifier of one of the caller's documents, live or archived, copied exactly as content__list_documents gives it.
expected_versionintegerrequired- The version of the document from the last time it was read with content__get_document or content__list_documents. Archiving advances the version, so a document archived since is not deleted: the call is refused with the current version so the document can be read again.
eracontextmcp_content__delete_folderDelete one of the caller's folders, which cannot be undone: a deleted folder is not restored, and creating its path again makes a new folder.DestructiveContent Delete Folder
Delete one of the caller's folders, which cannot be undone: a deleted folder is not restored, and creating its path again makes a new folder. Only an empty folder is deleted. A folder that still holds a folder or a document is refused as RESOURCE_CONFLICT and nothing is deleted, and an archived document counts as held, so a folder whose only contents are archived documents is not empty. Deleting a folder never deletes a document or a folder beneath it. The top level cannot be deleted. Use this only when the user asked for the folder to go, and tell the user which folder was deleted. The answer gives the folder's path and the instant it was deleted; repeating the call with the same expected_version answers the same instant without deleting anything again, so a repeat is safe, while a call with any other version finds no folder and is refused as not found. A document's or folder's version is the number a later change passes back as expected_version, so a change never overwrites an edit the agent has not seen. It advances with every change: read it again from a fresh result before using it, and never reuse one from an earlier read. If the folder has changed since expected_version was read, nothing is deleted and the call is refused as RESOURCE_CONFLICT with the folder's current version: read the folders again with content__list_folders, check that the deletion still makes sense, then repeat it with the version the new read gives. Changing the library needs the user's content write permission (mcp:content-write), which the user grants separately; without it the call is refused and the refusal names the permission. The document library is available only to accounts it is enabled for. For any other account every Content tool refuses with feature_disabled, which no retry changes, so tell the user the library is not on their account instead of trying again.
Inputs
expected_versionintegerrequired- The version of the folder from the last time it was read with content__list_folders. A folder that has changed since is not deleted: the call is refused with the current version so the folder can be read again.
pathstringrequired- The folder to delete, for example 'Taxes/2025', copied exactly as content__list_folders gives it. A path that is not one of the caller's folders is refused as not found.
eracontextmcp_knowledge__forgetDelete a stored financial fact from the user's profile.DestructiveKnowledge Forget
Delete a stored financial fact from the user's profile. Use when the user wants to clear an incorrect or outdated answer.
Inputs
slugstringrequired- Required. The slug of the fact to forget, copied from the fact as knowledge__get_financial_context_and_overview served it.
pack_slugstring- Optional; absent means 'financial-profile-v1'. The question pack's slug as knowledge__get_pending_questions served it, when the fact answers one of its questions.
qualifier_keystring- Optional; absent means the record with no period, place or kind. Send the qualifier_key of the record to forget, copied unchanged from the record as knowledge__recall_history or knowledge__get_financial_context_and_overview served it, or from the records a not-found answer lists; never write one.
recordstring- Optional; absent means the fact's general record. Send kind 'instance' with the instance_id a read served when the entry carries one, or kind 'general' for the record that belongs to no particular thing.
eracontextmcp_knowledge__reset_pack_questionsWarning: this cannot be undone — only call when you have high confidence the user wants to reset and re-surface all previously skipped or snoozed questions.DestructiveKnowledge Reset Pack Questions
Warning: this cannot be undone — only call when you have high confidence the user wants to reset and re-surface all previously skipped or snoozed questions. This operation reverts all Skipped and Snoozed question states back to Pending so they will be re-surfaced by the flow engine. It does not delete any stored facts or assertions — only the skip/snooze state is reset. Call knowledge__get_pending_questions after a successful reset to obtain the newly re-surfaced questions.
- Idempotent
Inputs
pack_slugstring- The question pack slug to reset. Defaults to 'financial-profile-v1' if omitted.
eracontextmcp_transactions__manage_manual_transactionCreate, update, or delete transactions on a manual account.DestructiveTransactions Manage Manual Transaction
Create, update, or delete transactions on a manual account. Amount must be a positive integer; use direction=outflow or inflow. Currency is required for create.
Inputs
account_group_keystringrequired- The account group projection key shared by all operations. Obtain from accounts__list_financial_accounts (the account_id field). Must be a manual account.
operationsarrayrequired- Array of transaction operations to execute sequentially. Each has its own action and fields.
preview_onlyboolean- When true, parse and validate all operations but do not write anything. Returns per-operation validation verdicts (valid/invalid + reason). Default: false.
No tools match.
