CFBD

Provides access to college football data from the College Football Data API via an MCP server for querying in Claude Desktop.

python

1

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "mcp-mirror-lenwood_cfbd-mcp-server": {
      "command": "uv",
      "args": [
        "run",
        "cfbd-mcp-server"
      ],
      "env": {
        "PATH": "/full/path/to/python",
        "CFB_API_KEY": "xxx"
      }
    }
  }
}

You can run the College Football Data MCP Server locally and connect it to Claude Desktop to query college football data via natural language. This server lets you access game results, team and player statistics, play-by-play data, rankings, and win probabilities, then use them in conversations or analyses without writing code.

How to use

Set up the MCP server and connect it to your client so you can ask questions like a0“Show me team rankings this season” or a0“Give me drive summaries for the latest game.” Start the server with the standard runtime command, then configure the client to point at the local MCP instance. You will see available analysis prompts and tooling in your client interface after the server is connected.

How to install

Prerequisites: you need Python and the UV package manager. You also need a College Football Data API key.

Install UV if you haven have it yet.
Clone the MCP server project and move into the directory.
Create and activate a virtual environment.
Install the server as a Python package.
Create a .env file in the project root and add your API key using the key CFB_API_KEY.
Start the MCP server using the runtime command shown below.

Configuration and connection

To connect Claude Desktop, add a stdio MCP configuration that runs the UV runtime and points to the cfbd-mcp-server entry. Use the environment placeholder for your API key and the full path to your Python runtime as shown.

{
  "mcpServers": {
    "cfbd": {
      "type": "stdio",
      "name": "cfbd",
      "command": "uv",
      "args": [
        "run",
        "cfbd-mcp-server"
      ],
      "env": {
        "CFB_API_KEY": "YOUR_API_KEY_HERE",
        "PATH": "/full/path/to/python"
      }
    }
  }
}

Troubleshooting

If you encounter API key errors, ensure your key is valid and set in both your .env file and the client configuration. If you hit rate limits, reduce request frequency or consider caching frequent queries. For connection issues, verify internet access and that the MCP server is running, then restart Claude Desktop after updating the configuration.

Notes on usage

This MCP server exposes endpoints and tools for querying games, records, plays, drives, play-by-play stats, rankings, and win-probability metrics. You can use prebuilt prompts to analyze games, teams, trends, rivalries, and more.

Available tools

get-games

Retrieve game data including scores and metadata for specified seasons or filters.

get-records

Fetch team season records and standings for a given conference or overall.

get-games-teams

Access detailed statistics for teams within specific games.

get-plays

Query play-by-play data for games, including sequences and outcomes.

get-drives

Analyze drive summaries and results across games or seasons.

get-play-stats

View statistics for individual plays, including key metrics.

get-rankings

Check team rankings across polls and periods.

get-pregame-win-probability

See win probabilities before games start.

get-advanced-box-score

Access advanced box score statistics for deeper analysis.