CFBD MCP Server

What does “CFBD” MCP Server do?

The CFBD MCP (Model Context Protocol) Server is a tool that connects AI assistants and applications with the College Football Data API, enabling advanced access to college football statistics and analytics. By acting as a bridge between AI models and this rich data source, CFBD MCP empowers users to query game results, team records, player statistics, play-by-play data, rankings, win probabilities, and more. This capability enhances development workflows for sports analytics, content generation, and research by allowing AI agents to retrieve and analyze real-time and historical college football data programmatically or via natural language. The server is designed for seamless integration with platforms like Claude Desktop, enabling AI-driven insights and automation around college football data.

List of Prompts

No specific prompt templates are listed in the available documentation or code. If the server exposes standardized prompt templates or workflows, they are not documented in the repository.

List of Resources

No explicit resources are described in the documentation or code. The server provides access to college football statistics through the CFBD API, but individual MCP resource primitives are not detailed.

List of Tools

No explicit tool list is provided in the available documentation or visible code structure. The repository states the server enables “CFBD API queries,” which likely map to tools for retrieving statistics, game data, player stats, etc., but these are not enumerated.

Use Cases of this MCP Server

• College Football Analytics
  Developers and analysts can use the MCP server to query comprehensive statistics, analyze team and player performance, and run custom queries for research or content creation.
• Game Results and Upset Detection
  Generate insights or reports on historical upsets, rankings, or match outcomes by leveraging detailed play-by-play and win probability data.
• AI-Powered Sports Content Generation
  Integrate the server into AI writing tools to automatically generate summaries, previews, or recaps using live or historical data.
• Team and Player Comparison
  Enable AI models to compare teams or players across seasons, using advanced metrics and statistics for scouting or fan engagement.
• Integration with AI Assistants
  Enhance conversational AI (e.g., Claude Desktop) to answer natural language queries about college football, including schedules, records, and advanced stats.

How to set it up

Windsurf

1. Ensure Python 3.11+ and the UV package manager are installed.
2. Clone the repository:

   git clone https://github.com/lenwood/cfbd-mcp-server
   cd cfbd-mcp-server
   

3. Set up a virtual environment and install dependencies:

   uv venv
   source .venv/bin/activate
   uv pip install -e .
   

4. Create a .env file with your API key:

   CFB_API_KEY=your_api_key_here
   

5. Configure Windsurf to include the CFBD MCP Server:

   {
     "mcpServers": {
       "cfbd": {
         "command": "python",
         "args": ["-m", "cfbd_mcp_server"],
         "env": {
           "CFB_API_KEY": "your_api_key_here"
         }
       }
     }
   }
   

6. Save and restart Windsurf. Verify by running a sample query.

Claude

1. Install as above, ensuring Python 3.11+ and UV.
2. Add the server to your Claude Desktop configuration (e.g., via claude_desktop_config.json):

   {
     "mcpServers": {
       "cfbd": {
         "command": "python",
         "args": ["-m", "cfbd_mcp_server"],
         "env": {
           "CFB_API_KEY": "your_api_key_here"
         }
       }
     }
   }
   

3. Restart Claude Desktop and verify connection.

Cursor

1. Clone the repository and set up as above.
2. In Cursor’s MCP configuration, add:

   {
     "mcpServers": {
       "cfbd": {
         "command": "python",
         "args": ["-m", "cfbd_mcp_server"],
         "env": {
           "CFB_API_KEY": "your_api_key_here"
         }
       }
     }
   }
   

3. Save and restart Cursor. Test with a query.

Cline

1. Follow installation steps for Python, UV, and dependencies.
2. In Cline’s settings, add the CFBD MCP Server:

   {
     "mcpServers": {
       "cfbd": {
         "command": "python",
         "args": ["-m", "cfbd_mcp_server"],
         "env": {
           "CFB_API_KEY": "your_api_key_here"
         }
       }
     }
   }
   

3. Restart Cline and verify connectivity.

Note about securing API keys:
Always store your API key in environment variables, not directly in code or checked-in files. In your MCP server config, use the env field as shown above to inject your key securely.

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "cfbd": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “cfbd” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Our opinion

This MCP server is clearly useful for college football data automation and analytics, and is well documented for setup and integration. However, it lacks documentation on reusable prompt templates, explicit MCP resource primitives, and a tool manifest, which are important for full MCP ecosystem compatibility and developer experience. For those focused on sports data, it’s a strong option, but broader MCP best practices could be better addressed.

MCP Score

Overall, I would rate this MCP server a 5/10: it serves its purpose and is open source, but lacks key MCP documentation and features such as explicit prompt, resource, and tool definitions. For sports analytics it is quite good, but for general MCP development, more detail is required.