MCP Server for NBA Stats Predictor Application

What is MCP Server for NBA Stats Predictor Application?

An MCP-powered tool that generates player performance forecasts for upcoming NBA games using real-time data analysis and advanced statistical modeling. It integrates with Claude Desktop, allowing users to query predictions via natural language.

How to use MCP Server for NBA Stats Predictor Application?

Clone the repository, install Python dependencies, download data, train the prediction model, start the FastAPI server, then run the MCP server with uv run mcp_main.py. Configure Claude Desktop by adding the server to claude_desktop_config.json with the correct project path. Once configured, ask Claude for player performance predictions.

Key features of MCP Server for NBA Stats Predictor Application

• Leverages real-time data analysis and statistical modeling
• Provides player performance forecasts for upcoming games
• Integrates with Claude Desktop via MCP protocol
• Requires local data download and model training
• Uses FastAPI as the backend server
• Handles all setup steps from a single repository

Use cases of MCP Server for NBA Stats Predictor Application

• Asking Claude Desktop to predict a player's points, rebounds, or assists for an upcoming game
• Comparing multiple player forecasts to inform fantasy basketball decisions
• Getting quick performance insights during game previews or analysis

FAQ from MCP Server for NBA Stats Predictor Application

What are the prerequisites for using this server?

Python 3.8+, pip, and Claude Desktop are required. A virtual environment is recommended.

How do I configure Claude Desktop to use this server?

Add an entry to claude_desktop_config.json with the command pointing to the project’s .venv/bin/uv and arguments including the project directory and run mcp_main.py. Replace the path placeholder with your actual project path.

What do I do if the MCP tool isn’t working?

Verify all paths in the configuration are correct, ensure the virtual environment is activated, all dependencies are installed, and the FastAPI server is running before using the MCP tool.

How do I run the MCP server after installation?

Open a terminal in the project directory, activate the virtual environment, then run uv run mcp_main.py. The server must be running for Claude Desktop to connect.

Do I need to train the prediction model myself?

Yes. After downloading the data with python3 data_pipeline/download_data.py, you must train the model using python3 models/train_model.py before the server can make predictions.