Provides access to live sports data and analytics from BALLDONTLIE: The Sports API
Config is the same across clients — only the file and path differ.
{
"mcpServers": {
"io-balldontlie-mcp": {
"command": "<see-readme>",
"args": []
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
A Model Context Protocol (MCP) server that provides access to comprehensive sports data from the BALLDONTLIE API, including NBA, WNBA, NFL, MLB, EPL, NHL, NCAAF, NCAAB, MMA, CS2, League of Legends, Dota 2, FIFA World Cup 2026, La Liga, Serie A, UEFA Champions League, Bundesliga, and Ligue 1 statistics, player information, game data, and more.
No automated test available for this server. Check the GitHub README for setup instructions.
Five weighted categories — click any category to see the underlying evidence.
No known CVEs.
No package registry to scan.
Be the first to review
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Others in analytics
MCP Server for GCP environment for interacting with various Observability APIs.
⚡ A Simple / Speedy / Secure Link Shortener with Analytics, 100% run on Cloudflare.
MCP server for InsightSentry financial data API - market data, options, screeners, and more
MCP server for Google Lighthouse performance metrics
MCP Security Weekly
Get CVE alerts and security updates for io.balldontlie/mcp and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
A Model Context Protocol (MCP) server that provides access to comprehensive sports data from the BALLDONTLIE API, including NBA, WNBA, NFL, MLB, EPL, NHL, NCAAF, NCAAB, MMA, CS2, League of Legends, Dota 2, FIFA World Cup 2026, La Liga, Serie A, UEFA Champions League, Bundesliga, and Ligue 1 statistics, player information, game data, and more.
npm install @balldontlie/mcp-server
Sign up at BALLDONTLIE to get your free API key.
Add to your MCP client configuration (e.g., Claude Desktop) to use the hosted server:
{
"mcpServers": {
"balldontlie-api": {
"url": "https://mcp.balldontlie.io/mcp",
"transport": "http",
"headers": {
"Authorization": "<YOUR_BALLDONTLIE_API_KEY>"
}
}
}
}
Replace <YOUR_BALLDONTLIE_API_KEY> with your actual API key from BALLDONTLIE.
Clone and run from source code:
git clone https://github.com/balldontlie-api/mcp-server.git
cd mcp-server
npm install
npm run build
npm start
Configure your MCP client to connect to the local server:
{
"mcpServers": {
"balldontlie-api": {
"url": "http://localhost:3000/mcp",
"transport": "http",
"headers": {
"Authorization": "<YOUR_BALLDONTLIE_API_KEY>"
}
}
}
}
The server will automatically provide all available tools. You can ask your AI assistant things like:
| Variable | Default | Description |
|---|---|---|
PORT | 3000 | Server port when running locally |
BACKEND_API_URL | https://api.balldontlie.io | BALLDONTLIE API base URL |
API_TIMEOUT | 30000 | Request timeout in milliseconds |
LOG_LEVEL | info | Logging level (error, warn, info, debug) |
NODE_ENV | development | Environment (development, production, test) |
ENABLE_DEBUG | false | Enable debug logging |
ENABLE_TRACING | false | Enable DataDog APM tracing (requires DD_AGENT_HOST) |
DD_AGENT_HOST | - | DataDog agent hostname for APM tracing |
DD_PROFILING_ENABLED | false | Enable DataDog profiling |
SERVICE_VERSION | 1.0.0 | Service version for tracing |