FinContext MCP Server
FinContext's remote MCP server for read-only personal finance. The provider's own llms.txt (https://fincontext.ai/llms.txt) documents 10 tools exposed over MCP JSON-RPC at https://fincontext.ai/mcp. The endpoint requires a per-user Bearer API token minted by POST /api/agent-signup or /api/agent-login; an anonymous tools/list to the documented endpoint returned HTTP 401 on 2026-11-07, so the live tool schemas are only reachable after authentication. Tool list below is recorded as documented, not as returned by a live server.
One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.
Endpoint
Hosted endpoint · transport
Connect
This is a remote MCP server — point an MCP client at the endpoint URL. Clients with native remote support (Claude, Cursor, VS Code, …):
For stdio-only clients (older Claude Desktop, etc.), bridge with mcp-remote:
If the server requires authentication, add the provider's token/header (e.g. an X-API-Key) per its docs. A quick reachability check:
Tools
balances— Get current account balances.transactions— Search and filter transactions by date, category, account, amount.categories— List all available spending categories.update— Override merchant name or category for a transaction.link_bank— Generate a Plaid Hosted Link URL to connect a bank account.status— Check if bank accounts are linked.stat— Run SQL SELECT queries against virtual `transactions` and `balances` tables. Supports GROUP BY, HAVING, aggregates (SUM, AVG, COUNT, STDDEV), date functions (date_trunc, EXTRACT). Max 1000 rows, 5s timeout.feedback— Send bug reports, feature requests, or praise. Takes `message` (required, up to 4000 chars) and optional `type` (bug | feature | praise | question | general). Rate limited to 5 per hour per user.sync— Pull latest transactions and balances from Plaid's cache. Asynchronous, returns immediately with status='started'. Rate limited to 5 per 5 minutes.help— Show available tools and detailed usage. Pass `subcommand` for details.
About MCP
The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.
Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.
Work with this as data
Every MCP server here is available over the APIs.io API and to AI agents over MCP.