The Financial Datasets MCP Server is an open-source Model Context Protocol server with 2,300+ stars on GitHub that lets Claude and other AI assistants pull live stock market data — financial statements, prices and news — straight into the conversation.
Large language models cannot see the market, so financial questions usually end in stale training data or a manual copy-paste from a terminal. This server, maintained by the Financial Datasets team and updated in 2025, bridges that gap through MCP, the open protocol for connecting AI assistants to external tools. Once configured, the assistant can call typed tools to fetch a company’s income statements, balance sheets and cash flow statements, get current and historical stock prices, read recent company news, and query cryptocurrency tickers and prices the same way. It is a focused, single-purpose server: it requires Python 3.10+ and the uv package manager, connects to the Financial Datasets API with your key, and exposes clean tool definitions that any MCP-compatible client can discover and call.
The MCP server is free and open source under the MIT license. It talks to the Financial Datasets API, which is a paid data service with its own plans and API key — check the official site for current pricing before building on it.
Developers and analysts building AI assistants, agents or research workflows that need reliable, structured stock market and crypto data available to the model at conversation time.