beanquery-mcp
16
The Beancount MCP Server is an experimental server designed for querying and analyzing financial data stored in Beancount ledger files. It leverages the Model Context Protocol for standardized communication with AI assistants, enhancing data accessibility. It includes various tools and resources for setting ledger files and running queries.
Beanquery MCP
The Beancount MCP Server is an experimental implementation of the Model Context Protocol (MCP) designed to interface with Beancount ledger files. It allows seamless querying and analysis of financial data using the Beancount Query Language (BQL) and beanquery tool. The server facilitates standardized communication with AI assistants to enhance the utility and accessibility of Beancount financial data.
Available Resources and Tools
- Tools:
- set_ledger_file: Set the Beancount ledger file for queries.
- run_query: Run a BQL query against the loaded Beancount file.
- Resources:
- beanquery://tables: List of tables accessible by BQL.
- beanquery://accounts: List of accounts in the Beancount file.
Privacy Warning
- Be cautious of transmitting confidential financial information to third-party services.
- Mask sensitive data in test ledgers and use self-hosted LLMs where possible.
Setup
- Requirements: Python 3.10 or later, uv for managing Python projects.
Usage
- Use development mode for testing and debugging.
- Integrate with Claude Desktop.
Testing
- Run
pytest
onserver_test.py
.
Contributing
- Fork the repository, create a feature branch, commit changes, push to branch, and open a pull request.
License
- Licensed under the MIT License.