About Finnhub MCP Server
Finnhub MCP Server connects MCP clients to Finnhub market data. It provides tools for stock quotes, financials, recommendation trends, and market news.
Key features
- 01Latest market news
- 02Stock quote data
- 03Basic stock financials
- 04Recommendation trends
Use cases
- 01Review recent market coverage
- 02Check a stock quote
- 03Inspect basic company financials
- 04View analyst recommendation trends
MCP support
It exposes Finnhub API data through MCP tools for clients, including market news, stock quotes, financials, and recommendation trends.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEFinnhub MCP Server
An MCP server to interface with Finnhub API.
Tools
-
list_news- List latest market news from Finnhub market news endpoint
-
get_market_data- Get market data for a particular stock from quote endpoint
-
get_basic_financials- Get basic financials for a particular stock from basic financials endpoint
-
get_recommendation_trends- Get recommendation trends for a particular stock from recommendation trend endpoint
Configuration
-
Run
uv syncto install the dependencies. To installuvfollow the instructions here. Then dosource .venv/bin/activate. -
Setup the
.envfile with the Finnhub API Key credentials.
FINNUB_API_KEY=<FINNHUB_API_KEY>
-
Run
fastmcp install server.pyto install the server. -
Open the configuration file located at:
- On macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - On Windows:
%APPDATA%/Claude/claude_desktop_config.json
- On macOS:
-
Locate the command entry for
uvand replace it with the absolute path to theuvexecutable. This ensures that the correct version ofuvis used when starting the server. -
Restart Claude Desktop to apply the changes.
Development
Run fastmcp dev server.py to start the MCP server. MCP inspector is helpful for investigating and debugging locally.
Comments
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.