Feyod MCP Server

What is Feyod MCP Server?

A FastMCP-based Model Context Protocol (MCP) server for querying Feyenoord football match data using natural language. It is compatible with Claude Desktop and other MCP clients, and is publicly available at https://mcp.feyod.nl/mcp.

How to use Feyod MCP Server?

Connect via any MCP-compatible client to the public endpoint, or run the server locally using Docker (jeroenvdmeer/feyod-mcp) or Python with provided setup. The exposed tool is query_feyod_database, which converts a natural language query into SQL and returns results.

Key features of Feyod MCP Server

• Converts natural language questions to SQL queries.
• Uses LangChain for SQL generation, validation, and correction.
• Supports multiple LLM providers (e.g., OpenAI, Google).
• Public endpoint available for direct MCP client access.
• Docker container available on Docker Hub.
• Local setup with SQLite database from the feyod GitHub repository.

Use cases of Feyod MCP Server

• Ask about Feyenoord match results in plain English.
• Query player statistics and historical performance data.
• Integrate Feyenoord data into AI assistants via MCP.
• Build custom dashboards or reports using the returned SQL.

FAQ from Feyod MCP Server

What data does Feyod MCP Server query?

It queries Feyenoord Open Data from a SQLite database maintained in the feyod GitHub repository.

What are the runtime dependencies?

Python 3.10+, MCP Python SDK, LangChain, a SQLite database, and an API key for the chosen LLM provider (e.g., OpenAI, Google).

How do I configure a different LLM provider?

Set LLM_PROVIDER and LLM_API_KEY in the .env file, install the corresponding LangChain package (e.g., langchain-google-genai), and ensure the provider is defined in llm_factory.py.

Is this server affiliated with Feyenoord Rotterdam?

No. The initiative is not affiliated with Feyenoord Rotterdam N.V. and is not an official Feyenoord product.

Where can I find the database file?

The database is built from the SQL file in the feyod repository. You must obtain the latest feyod.sql file and create feyod.db locally, or use the database included in the Docker image.