mcpField
B
Beancount MCP (Model Context Protocol) Server

Beancount MCP (Model Context Protocol) Server

Local
github.com/StdioAFinance11Updated 77w ago
Repository

About Beancount MCP (Model Context Protocol) Server

Beancount MCP is an MCP server for querying a Beancount ledger and submitting transactions. It is intended for users who want MCP clients to work with their ledger.

Key features

  1. 01Query a Beancount ledger
  2. 02Submit ledger transactions
  3. 03stdio and SSE transports

Use cases

  1. 01Run queries against a ledger
  2. 02Submit a transaction to a ledger

MCP support

The MCP server exposes Beancount ledger queries and transaction submission to MCP clients. It supports stdio and SSE transports.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "beancount": {
      "command": "uvx",
      "args": [
        "beancount-mcp"
      ]
    }
  }
}
Run commanduvx beancount-mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypibeancount-mcp

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Beancount MCP (Model Context Protocol) Server

A Beancount MCP server which can execute beancount query, and submit transaction to the ledger.

Usage

uvx beancount-mcp [--transport=stdio/sse] your_ledger.bean

Add to Claude

Add to claude_desktop_config.json (you can find this file by using Settings - Developer - Edit Config):

{
  "mcpServers": {
    "https://github.com/StdioA/beancount-mcp/tree/master": {
      "command": "uvx",
      "args": [
        "beancount-mcp",
        "--transport=stdio",
        "PATH_TO_YOUR_LEDGER"
      ],
      "disabled": false,
      "autoApprove": []
    }
  }
}

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.