Balldontlie MCP Server

An MCP Server implementation that integrates the Balldontlie API, to provide information about players, teams and games for the NBA, NFL and MLB.

Tools

• get_teams

• get_players

• get_games

• get_game

Prompts

• schedule_generator

Given a league (NBA, MLB, NFL), a starting date and ending date generates an interactive schedule in Claude Desktop.

Sample queries

With this MCP Server installed you can ask Claude or other LLM questions like the following.

Show me today's baseball games.
Can you find football players with the last name Purdy?
How many NBA players have the last name Ming?

Configuration

Getting an API Key

1. Sign up for account at Balldontlie.io

2. The free plan is enough for this MCP Server

Installing using Desktop Extension (DXT)

1. Download the `dxt` file from the Releases

2. Open it with Claude Desktop

or

Go to File -> Settings -> Extensions and drag the .DXT file to the window to install it

Installing via Smithery

To install balldontlie-mcp for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @mikechao/balldontlie-mcp --client claude

Usage with Claude Desktop

Add this to your `claude_desktop_config.json`:

{
  "mcp-servers": {
    "balldontlie": {
      "command": "npx",
      "args": [
        "-y",
        "balldontlie-mcp"
      ],
      "env": {
        "BALLDONTLIE_API_KEY": "YOUR API KEY HERE"
      }
    }
  }
}

Usage with LibreChat

mcpServers:
  balldontlie:
    command: sh
    args:
      - -c
      - BALLDONTLIE_API_KEY=your-api-key-here npx -y balldontlie-mcp

License

This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.

Disclaimer

This library is not officially associated with balldontlie.io. It is a third-party implementation of the balldontlie api with a MCP Server.

Hosted deployment

A hosted deployment is available on Fronteir AI.