FinanceToolkit
An open-source Python library of more than 500 financial analysis methods, written to be fully transparent about their calculations, with an optional MCP server for querying them without code.
FinanceToolkit is an open-source Python toolkit in which more than 500 financial methods are written down in the simplest way possible, so their calculation is fully transparent and reproducible. The project was built after its author found the same financial metric, such as a company's price-to-earnings ratio, reported differently by different data sources because each used a different, often undocumented, method.
It covers equities as well as options, currencies, cryptocurrencies, ETFs, mutual funds, indices, money markets, and commodities, and pairs with a separate Finance Database of over 300,000 symbols so tickers found there can be fed into the toolkit for historical data and performance and risk measurements such as the Sharpe ratio and Value at Risk. The toolkit is also available as an MCP server, so its methods can be queried from Claude, Copilot, Cursor, Windsurf, or any other MCP-compatible client without writing code, either through a hosted endpoint or a local server.