NBA Player Stats is an MCP server that provides comprehensive NBA player statistics retrieved directly from basketball-reference.com. It connects LLM-based assistants to historical and current basketball data across twenty-three specialized tools. Designed for sports analysts, fantasy basketball players, researchers, and sports enthusiasts, the server allows users to query traditional and modern analytics without manual database searches. It enables users to retrieve complete career totals, per-game figures, per-36 minute statistics, and advanced efficiency metrics such as PER, True Shooting Percentage, Win Shares, BPM, and VORP. The server also handles granular queries like year-by-year playoff records, head-to-head player comparisons, team-specific matchups, monthly splits, situational splits, and single-game highs. Assistants running this tool can track career trajectories, evaluate historical milestones, inspect award voting outcomes, and source player headshot URLs directly from basketball-reference.com within ongoing conversational workflows.
Category: Other & General Purpose
Tags: basketball, data, nba, sports, statistics
pip install nba-player-stats-mcp or clone the repository via git clone https://github.com/ziyadmir/nba-player-stats-mcp and run pip install -r requirements.txt. 3. Add the server to your Claude Desktop configuration file (claude_desktop_config.json) under mcpServers: json { "mcpServers": { "nba-player-stats": { "command": "python", "args": ["path/to/basketball/src/server.py"], "cwd": "path/to/basketball" } } } 4. If installed globally through PyPI, you can alternatively execute nba-player-stats-server to run the service directly. 5. Restart Claude Desktop to start using the tools.Part of MCP Servers
You can install the server via pip using the command pip install nba-player-stats-mcp. Alternatively, you can clone the GitHub repository, install dependencies from requirements.txt, and run the server script directly with Python.
The server provides 23 tools for fetching basketball-reference.com data. It handles career stats, per-game averages, per-36 numbers, advanced metrics like BPM and Win Shares, game logs, shooting splits, awards voting history, headshots, and situational splits.
It works with any MCP-compliant client, including Claude Desktop. You configure it by specifying the Python command and server script path within your client configuration file.
The server pulls its player metrics, historical achievements, season game logs, and profile pictures directly from basketball-reference.com using integrated scraping functions.