NBA MCP Server

What does “NBA” MCP Server do?

The NBA MCP Server is a Model Context Protocol (MCP) server designed to enhance AI assistants, such as Anthropic’s Claude, by enabling them to access and retrieve up-to-date NBA basketball game data and statistics. By interfacing with the open-source nba_api, the server allows LLMs to fetch recent NBA game scores, player statistics, and advanced analytics that would otherwise be inaccessible due to model knowledge limitations. This connection empowers AI-driven development workflows, allowing for dynamic database queries and live data retrieval regarding NBA games, player performance, and more, thus significantly augmenting the assistant’s ability to interact with and analyze real-world sports data.

List of Prompts

No prompt templates were specified in the repository.

List of Resources

No explicit resources were detailed in the repository.

List of Tools

• Fetch final scores
  Retrieves the final scores for all NBA games that occurred yesterday or in the recent past.

• Fetch basic player stats
  Obtains points, rebounds, and assists (P/R/A) breakdowns for all players who participated in games from yesterday or earlier dates.

• Fetch full player stats
  Collects comprehensive player stats including PTS, REB, AST, STL, BLK, TO, PLUS_MINUS, and MIN for games played yesterday or in the past.

• Fetch four factors
  Retrieves the “four factors” advanced analytics for all NBA games that happened yesterday or in the recent past.

Use Cases of this MCP Server

• Real-time NBA game summaries
  Developers can enable AI assistants to answer questions about the latest NBA games, providing up-to-date scores and outcomes.

• Detailed player performance analysis
  The server allows retrieval of per-player statistics, supporting use cases like generating post-game reports, fantasy basketball insights, or historical analysis.

• Advanced analytics for sports journalism
  By accessing the four factors and other metrics, journalists and analysts can quickly surface advanced stats for articles or commentary.

• Automated sports dashboards
  Integration with dashboard tools allows live updates on NBA games and player performances for fans or analysts.

• AI-driven sports applications
  Developers can use the server to power chatbots or virtual assistants capable of answering NBA-related queries with recent data.

How to set it up

Windsurf

1. Ensure Python is installed and set up a virtual environment in the repo directory.
2. Run:

   uv venv
   .venv\Scripts\activate
   uv pip install -e .
   

3. Add the NBA MCP Server configuration to your Windsurf config (if supported).
4. Insert the NBA MCP server in the mcpServers object with the appropriate command and arguments.
5. Save and restart the Windsurf service.
6. Verify the setup by running a test query.

JSON example:

{
  "mcpServers": {
    "nba-mcp": {
      "command": "python",
      "args": ["nba.py"]
    }
  }
}

Claude

1. Clone the repo and set up the environment as above.
2. Install dependencies:

   uv venv
   .venv\Scripts\activate
   uv pip install -e .
   

3. Edit your Claude configuration file to add the NBA MCP Server.
4. Add the server under the mcpServers section.
5. Restart Claude and verify connectivity.

JSON example:

{
  "mcpServers": {
    "nba-mcp": {
      "command": "python",
      "args": ["nba.py"]
    }
  }
}

Cursor

1. Clone the repository and set up the virtual environment.
2. Install requirements as previously described.
3. Edit Cursor’s configuration to include the NBA MCP Server.
4. Add the server entry and save changes.
5. Restart Cursor and test functionality.

JSON example:

{
  "mcpServers": {
    "nba-mcp": {
      "command": "python",
      "args": ["nba.py"]
    }
  }
}

Cline

1. Ensure Python and virtual environment are set up.
2. Install the NBA MCP Server as above.
3. Edit the Cline configuration file.
4. Add the NBA MCP server details under mcpServers.
5. Restart Cline and run a test.

JSON example:

{
  "mcpServers": {
    "nba-mcp": {
      "command": "python",
      "args": ["nba.py"]
    }
  }
}

Securing API Keys

No API keys are required for the NBA MCP Server as it uses the open-source nba_api. If future versions require keys, you can secure them using environment variables:

JSON example:

{
  "mcpServers": {
    "nba-mcp": {
      "command": "python",
      "args": ["nba.py"],
      "env": {
        "NBA_API_KEY": "${NBA_API_KEY}"
      },
      "inputs": {
        "NBA_API_KEY": "your_api_key_here"
      }
    }
  }
}

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:

{
  "nba-mcp": {
    "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 “nba-mcp” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Based on the available information, the NBA MCP Server offers valuable real-time sports data integration for LLMs but is missing documentation on prompt templates, explicit resource definitions, and advanced MCP features like roots or sampling. It is a functional but basic implementation.

MCP Score

Rating:
I would rate this MCP server a 4 out of 10. It delivers its core functionality (NBA stats tools) and basic setup but lacks thorough documentation, resource definition, prompt templates, and advanced MCP features (roots, sampling). The absence of a license is also a significant limitation for open source use.