NBA Stats MCP server for AI agents

This NBA MCP server provides access to NBA statistics and live game data through the Model Context Protocol (MCP), serving as a bridge between applications and the NBA's data services.

Installation

Using Docker (Recommended)

Clone the repository:

git clone https://github.com/obinopaul/nba-mcp-server.git
cd nba-mcp-server

Install dependencies:
```
pip install -r requirements.txt
```
Build the Docker image:
```
docker build -t nba_mcp_server .
```

Run the Docker container:

docker run -d -p 5000:5000 --name nba_mcp_server nba_mcp_server

Add this to your claude_desktop_config.json:

{
  "mcpServers": {
    "nba_mcp_server": {
      "command": "docker",
      "args": [
        "exec",
        "-i",
        "nba_mcp_server",
        "python",
        "nba_server.py"
      ]
    }
  }
}

Direct Python Execution

Clone the repository:

git clone https://github.com/obinopaul/nba-mcp-server.git
cd nba-mcp-server

Create a new environment:

conda create --name your_env_name python=3.13
conda activate your_env_name

Install dependencies:
```
pip install -r requirements.txt
```
Run the NBA MCP server:
```
mcp run nba_server.py
```

Add this to your claude_desktop_config.json:

{
  "mcpServers": {
    "nba_mcp_server": {
      "command": "/path/to/your/python",
      "args": [
        "/path/to/nba_server.py"
      ]
    }
  }
}

After configuration, restart Claude Desktop to load the NBA server.

Available Tools

Live Game Data

nba_live_scoreboard: Fetches today's NBA scoreboard with game IDs, start times, scores, and broadcast details
nba_live_boxscore: Retrieves real-time box score for a given NBA game ID with detailed player and team statistics
nba_live_play_by_play: Gets live play-by-play actions for a specific game including scoring plays, fouls, timeouts, and substitutions

Player Information

nba_common_player_info: Retrieves basic information about a player (biographical data, height, weight, team, position)
nba_player_career_stats: Obtains a player's career statistics in different formats (per game, totals, per 36 minutes)
nba_list_active_players: Returns a list of all currently active NBA players
nba_player_game_logs: Obtains a player's game statistics within a specified date range

Team Data

nba_team_game_logs_by_name: Fetches a team's game logs using the team name
nba_fetch_game_results: Fetches game results for a given team ID and date range
nba_team_standings: Fetches NBA team standings for a given season and season type
nba_team_stats_by_name: Fetches team statistics using the team name with different aggregation methods
nba_all_teams_stats: Fetches statistics for all NBA teams across multiple seasons

Schedule Information

nba_list_todays_games: Returns scoreboard data for any specific date

Usage

Start the server:

python nba_server.py
# or
mcp run nba_server.py

The server runs with a 30-second timeout for more reliable operation and includes signal handlers for graceful shutdown (Ctrl+C).

Once configured and running, you can use all the NBA data tools in your conversations with Claude through Claude Desktop.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "nba_mcp_server" '{"command":"docker","args":["exec","-i","nba_mcp_server","python","nba_server.py"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "nba_mcp_server": {
            "command": "docker",
            "args": [
                "exec",
                "-i",
                "nba_mcp_server",
                "python",
                "nba_server.py"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "nba_mcp_server": {
            "command": "docker",
            "args": [
                "exec",
                "-i",
                "nba_mcp_server",
                "python",
                "nba_server.py"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect