AI Expense Tracker MCP for logging expenses, searching transactions, and generating budget reports from chat.
Scored across 13 tools
Most tools have clearly distinct roles, but log_transaction and record_expense both create expenses, and get_summary/get_report both aggregate spending. The explicit descriptions (structured fields vs. natural language, summary vs. grouped report) reduce ambiguity enough to avoid serious misselection.
Every tool follows a consistent verb_noun snake_case convention (delete_, get_, list_, log_, parse_, record_, restore_, search_, undo_, update_). Verbs clearly signal the action, and nouns identify the resource, making the pattern predictable across the whole set.
Thirteen tools is well within the ideal range for an expense-tracking server, and each tool maps to a distinct lifecycle, reporting, or account-management need. The count feels appropriately scoped without redundancy or bloat.
The server covers the full expense lifecycle: structured and natural-language creation, search, update, soft-delete, restore, undo, plus reporting and account settings. Minor gaps exist, such as no direct fetch-by-ID endpoint and no category management, but agents can work around them using search and existing tools.
Soft-delete an existing transaction by ID so it no longer appears in normal spending summaries.
Inputs: transaction_id (required), deleted_reason, client_request_id. Returns: object
Return the PocketLedger account linked to this chat session, including profile details and connected AI apps. Call when the user asks who they are logged in as, which account is connected, or which apps have access.
Inputs: no named parameters. Returns: object
Return a grouped expense spending report by category, merchant, day, week, month, or currency, with chart-ready structured data. Do not use the natural-language query as a keyword filter.
Inputs: query, period, date_to, category, +8 more. Returns: object
Return a spending summary for expenses in today, yesterday, this week, this month, this year, or a custom date range. Do not create income, transfers, or financial advice.
Inputs: period (required), date_to, timezone, date_from, +1 more. Returns: object
List expense categories available for classifying transactions. This only lists categories and must not be used for investment advice, income creation, or bank credential storage.
Inputs: include_custom, include_inactive. Returns: object
Create one personal expense transaction from explicit structured fields. Expense-only: do not use for income, salary deposits, account transfers, bank credential storage, budgets, investment advice, or calendar tasks.
Inputs: date (required), amount (required), category (required), currency (required), +8 more. Returns: object
Parse natural-language expense text without saving it, returning candidate amount, currency, merchant, category, date, and missing fields.
Inputs: text (required), locale, timezone, date_context, +1 more. Returns: object
Record one personal expense from natural-language text. Expense-only: do not use for income, salary deposits, account transfers, bank credential storage, budgets, investment advice, or calendar tasks.
Inputs: text (required), locale, timezone, date_context, +4 more. Returns: object
Restore a previously deleted transaction by ID so it appears in spending summaries again.
Inputs: transaction_id (required), client_request_id. Returns: object
Search a user's saved expense transactions by date range, category, merchant, keyword, currency, deleted status, and limit. Do not use for investment advice, income creation, bank credential storage, or calendar tasks.
Inputs: limit, cursor, period, date_to, +7 more. Returns: object
Undo the most recent supported transaction action, such as create, update, delete, or restore, within the undo window.
Inputs: operation, transaction_id, client_request_id, confirmation_token. Returns: object
Update the authenticated user's PocketLedger defaults for expense currency, reporting currency, timezone, and locale. Use this for account preferences only, not transaction edits, wallet balances, payments, or subscriptions.
Inputs: default_locale, default_currency, default_timezone, reporting_currency. Returns: object
Update an existing transaction by ID, changing fields such as amount, currency, merchant, category, date, timezone, or note.
Inputs: transaction_id (required), date, note, amount, +8 more. Returns: object
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Add one secure layer between your agents and this server.
