Sponsored by Deepsite.site

College Football Data MCP Server

Created By
lenwooda year ago
An MCP server enabling CFBD API queries within Claude Desktop.
Content

College Football Data MCP Server

An MCP server implementation providing access to college football statistics sourced from the College Football Data API V2 within Claude Desktop.

Python Version CFBD API Version MIT License smithery badge

Overview

This Model Context Protocol (MCP) server enables AI assistants and applications to:

  • Query comprehensive college football statistics and data
  • Access game results, team records, and player statistics
  • Analyze play-by-play data and drive summaries
  • View rankings and win probability metrics
  • Compare team performances and generate insights

Users can run queries using natural language.

Sample output

Q. What was the largest upset among FCS games during the 2014 season?

A. Let me help find the biggest FCS upset from 2014. I'll look through the games data, focusing on games between FCS teams where there was a significant gap in team strength and an unexpected outcome.

The data suggests there were several notable upsets in FCS during 2014, but one that stands out was Eastern Washington defeating Washington 52-59 on September 6th, 2014. This was particularly significant because:

  1. Washington was an FBS team from the Pac-12 conference
  2. The game was played at Washington's home stadium (Husky Stadium)
  3. Eastern Washington's win probability was only 1.4% according to the post-game stats
  4. The 59 points Eastern Washington scored was the most ever by an FCS team against a Pac-12 opponent
  5. Washington had been favored by multiple scores going into the game

Other notable FCS upsets from that season included:

  • North Dakota State defeating Iowa State 34-14
  • Bethune-Cookman defeating FIU 14-12
  • Northern Iowa nearly upsetting Iowa (lost 31-23)

However, Eastern Washington over Washington appears to be the largest upset of the 2014 FCS season when considering:

  • The difference in divisions (FCS vs FBS)
  • The caliber of the FBS opponent (Power 5 conference)
  • The scoring margin and offensive performance by the underdog
  • The historical significance as one of the highest-scoring FCS wins over a Power 5 team
  • The fact it happened on the road in a hostile environment

Prerequisites

Installation

Installing via Smithery

To install College Football Data Server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install cfbd --client claude
  1. Clone this repository:
git clone https://github.com/yourusername/cfbd-mcp-server
cd cfbd-mcp-server
  1. Create and activate a virtual environment:
uv venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate
  1. Install dependencies:
uv pip install -e .
  1. Create a .env file in the project root and add your API key:
CFB_API_KEY=your_api_key_here

Manual Installation

  1. Clone this repository:
git clone https://github.com/yourusername/cfbd-mcp-server
cd cfbd-mcp-server
  1. Create and activate a virtual environment:
uv venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate
  1. Install dependencies:
uv pip install -e .
  1. Create a .env file in the project root and add your API key:
CFB_API_KEY=your_api_key_here

Usage

Running the Server

Start the server:

uv run cfbd-mcp-server

Connecting with Claude Desktop

  1. Open your Claude Desktop configuration at:

    • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
    • Windows: %APPDATA%\Claude\claude_desktop_config.json
  2. Add the server configuration:

{
    "mcpServers": {
        "cfbd-mcp-server": {
            "command": "uv",
            "args": [
                "--directory",
                "/full/path/to/cfbd-mcp-server",
                "run",
                "cfbd-mcp-server"
            ],
            "env": {
                "CFB_API_KEY": "xxx",
                "PATH": "/full/path/to/python"
            }
        }
    }
}
  1. Close then restart Claude Desktop

Once you restart you can confirm the installation by clicking on the plus sign in the lower left corner of the text box. If successful you'll see "Add from cfbd-mcp-server" as one of the menu options. Here's an example screenshot.

Screenshot of successful install

Updating after install

  1. Download the updated files
cd cfbd-mcp-server
git pull
  1. Uninstall the existing package:
uv pip uninstall cfbd-mcp-server
  1. Delete existing build artifacts and metadata

For Windows:

rmdir /s /q build dist
del /s /q *.egg-info

For macOS:

rm -rf build dist *.egg-info
  1. Install the revised package and its dependencies
uv pip install -e .
uv sync --dev --all-extras
uv run cfbd-mcp-server
  1. Close and restart Claude Desktop

Features

Resources

Access schema documentation for all endpoints:

  • schema://games - Game information and scores
  • schema://records - Team season records
  • schema://games/teams - Detailed team game data
  • schema://plays - Play-by-play information
  • schema://drives - Drive summaries and results
  • schema://play/stats - Individual play statistics
  • schema://rankings - Team rankings across polls
  • schema://metrics/wp/pregame - Pregame win probabilities
  • schema://game/box/advanced - Advanced box score statistics

Tools

Query endpoints directly:

  • get-games - Retrieve game data
  • get-records - Get team records
  • get-games-teams - Access team game statistics
  • get-plays - Query play-by-play data
  • get-drives - Analyze drive information
  • get-play-stats - View play statistics
  • get-rankings - Check team rankings
  • get-pregame-win-probability - See win probabilities
  • get-advanced-box-score - Access detailed game statistics and analytics

Prompts

Pre-built analysis templates:

  • analyze-game - Get detailed analysis of a specific game
  • analyze-team - Comprehensive single team analysis
  • analyze-trends - Analyze trends over a season
  • compare-teams - Compare performance of two teams
  • analyze-rivalry - Analyze historical rivalry matchups

API Limits

The College Football Data API is free to use but has rate limiting:

  • Free tier: Limited requests per minute
  • CFBD Patreon subscribers get higher rate limits
  • Use efficient querying patterns to avoid hitting limits
  • Handle rate limit errors gracefully

Development

Project Structure

cfbd-mcp-server/
├── README.md
├── pyproject.toml
└── src/
    └── cfbd_mcp_server/
        ├── .env
        ├── __init__.py
        ├── cfbd_schema.py
        ├── schema_helpers.py
        └── server.py

Setting Up for Development

  1. Clone the repository
  2. Install development dependencies:
uv pip install -e ".[dev]"
  1. Run tests:
pytest

Contributing

  1. Fork the repository
  2. Create a feature branch
  3. Commit your changes
  4. Push to your fork
  5. Submit a pull request

Troubleshooting

Common Issues

  1. API Key Errors

    • Verify your API key is correctly set in both the .env and claude_desktop_config.json files
    • Check the key is valid at collegefootballdata.com
  2. Rate Limiting

    • Space out requests when possible
    • Consider Patreon subscription for higher limits
    • Implement caching for frequently accessed data
  3. Connection Issues

    • Verify internet connectivity
    • Check API status at collegefootballdata.com
    • Ensure proper error handling in your code

Getting Help

License

This project is licensed under the MIT License - see the LICENSE file for details.

Acknowledgments

Recommend Servers
TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.
Playwright McpPlaywright MCP server
Serper MCP ServerA Serper MCP Server
Visual Studio Code - Open Source ("Code - OSS")Visual Studio Code
MCP AdvisorMCP Advisor & Installation - Use the right MCP server for your needs
TimeA Model Context Protocol server that provides time and timezone conversion capabilities. This server enables LLMs to get current time information and perform timezone conversions using IANA timezone names, with automatic system timezone detection.
Jina AI MCP ToolsA Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.
Howtocook Mcp基于Anduin2017 / HowToCook (程序员在家做饭指南)的mcp server,帮你推荐菜谱、规划膳食,解决“今天吃什么“的世纪难题; Based on Anduin2017/HowToCook (Programmer's Guide to Cooking at Home), MCP Server helps you recommend recipes, plan meals, and solve the century old problem of "what to eat today"
Tavily Mcp
BlenderBlenderMCP connects Blender to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Blender. This integration enables prompt assisted 3D modeling, scene creation, and manipulation.
AiimagemultistyleA Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.
ChatWiseThe second fastest AI chatbot™
Amap Maps高德地图官方 MCP Server
WindsurfThe new purpose-built IDE to harness magic
MiniMax MCPOfficial MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.
EdgeOne Pages MCPAn MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.
CursorThe AI Code Editor
Context7Context7 MCP Server -- Up-to-date code documentation for LLMs and AI code editors
Baidu Map百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
DeepChatYour AI Partner on Desktop
Zhipu Web SearchZhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.