Nba Stats Predictor MCP

🚀 NBA Data Prediction Application's MCP Server

This is an MCP-based tool designed for NBA data prediction applications. It leverages real-time data analysis and advanced statistical modeling to generate player performance predictions.

🚀 Quick Start

After configuration, you can use the NBA data prediction tool in Claude Desktop to obtain player performance predictions for upcoming games.

📦 Installation

Prerequisites

• Python 3.8 or higher
• pip package manager
• Claude Desktop

Step-by-step Installation Instructions

1. Clone this repository to your local device.

2. Navigate to the project directory:

   cd nba-stats-predictor-application
   

3. Create a virtual environment:

   python3 -m venv venv
   

4. Activate the virtual environment:

   source venv/bin/activate
   

5. Install dependencies:

   pip install -r requirements.txt
   

6. Download the required data:

   python3 data_pipeline/download_data.py
   

7. Train the prediction model:

   python3 models/train_model.py
   

8. Start the FastAPI server:

   uvicorn api.fastapi_server:app --reload
   

9. Open a new terminal window.

10. Return to the project directory.

11. Install the UV package manager:

    curl -LsSf https://astral.sh/uv/install.sh | sh
    

12. Restart the current terminal.

13. Run the MCP server:

    uv run mcp_main.py
    

14. Open another new terminal window.

15. Configure Claude Desktop:

    code ~/Library/Application\ Support/Claude/claude_desktop_config.json
    

    Note: If the file does not exist, please create it.

16. Add the following configuration to the claude_desktop_config.json file:

    {
        "mcpServers": {
            "NBA-stats-predictor": {
                "command": "/actual_path/project_directory/.venv/bin/uv",
                "args": [
                    "--directory",
                    "/actual_path/project_directory/",
                    "run",
                    "mcp_main.py"
                ]
            }
        }
    }
    

    Please replace /actual_path/project_directory/ with your actual project path.

17. Now you should be able to use this MCP tool in Claude Desktop.

🔧 Troubleshooting

• Ensure that all paths in the configuration file are correct.
• Make sure the virtual environment is activated before running commands.
• Check if all dependencies are installed correctly.
• Confirm that the FastAPI server is running before starting it.