Beanquery (Beancount Ledger) MCP server

The Beancount MCP Server is an experimental implementation of the Model Context Protocol (MCP) that interfaces with Beancount ledger files. It allows you to query and analyze financial data stored in Beancount format using the Beancount Query Language (BQL), making financial data more accessible through standardized communication between AI assistants and Beancount ledgers.

Installation Requirements

Before installing the Beancount MCP Server, ensure you have:

• Python 3.10 or later
• uv for managing Python projects (recommended)

Setting Up the Server

You can run the Beancount MCP Server in two main modes:

Development Mode

To test and debug the server using the MCP Inspector:

mcp dev server.py

Claude Desktop Integration

To install the server into Claude Desktop:

mcp install server.py

For a quick start with the sample ledger:

uv run mcp install server.py -v BEANCOUNT_LEDGER=$(pwd)/sample.bean --with beancount --with beanquery

To give the server a custom name:

uv run mcp install server.py --name "Beanquery MCP Server" --with beancount --with beanquery

You can also set environment variables:

uv run mcp install server.py -v BEANCOUNT_LEDGER=/path/to/your/ledger.bean --with beancount --with beanquery

Or use an environment file:

uv run mcp install server.py -f .env --with beancount --with beanquery

Using the Server

The Beancount MCP Server provides several tools and resources for interacting with your Beancount ledger files:

Available Tools

• set_ledger_file: Set the Beancount ledger file to use for queries (if not already set via environment variable)
• run_query: Run a BQL query against the loaded Beancount file

Available Resources

• beanquery://tables: Get a list of tables that BQL can access
• beanquery://accounts: Get a list of accounts in the loaded Beancount file

Privacy Considerations

⚠️ Important Privacy Warning

This tool interfaces with language model providers (LLMs) via the MCP, and may transmit parts of your Beancount ledger—including potentially confidential financial information—to third-party services.

Use with caution when:

• Your ledger contains sensitive data (e.g., client names, salary details, health-related expenses)
• You are using a cloud-hosted or non-self-hosted LLM backend

Recommendations:

• Mask or redact sensitive data in test ledgers
• Use self-hosted LLMs when possible
• Review the data being sent via MCP to ensure compliance with your privacy requirements

Testing

To run the test suite:

pytest server_test.py

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "beanquery" '{"command":"python","args":["-m","server"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "beanquery": {
            "command": "python",
            "args": [
                "-m",
                "server"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "beanquery": {
            "command": "python",
            "args": [
                "-m",
                "server"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect