formula1
MCP server from Panth1823/formula1-mcp
claude mcp add --transport stdio panth1823-formula1-mcp node <path-to-your-cloned-repo>/build/index.js
How to use
The Formula1 MCP Server brings both historical Formula 1 data and live telemetry into the Model Context Protocol ecosystem. It exposes a set of tools to fetch historical results, timing data, driver and constructor standings, weather, pit stops, team radios, and more, sourced from OpenF1 (free historical data) and Ergast (legacy data). Real-time live data and MQTT streaming are supported for active sessions, though live streaming requires a paid OpenF1 account. When active, you can retrieve current car telemetry, positions, weather, and race control messages via the live tools, or fall back to REST endpoints for delayed data.
To use the server with Claude Desktop (or any MCP client), configure your mcpServers entry to point to the Node build output. The server provides tools such as getLiveCarData, getLivePositions, getLiveWeather, getHistoricRaceResults, getDriverStandings, getLapTimes, and getWeatherData, among others. Historical tools require you to first obtain a session key via getHistoricalSessions before requesting data tied to a specific race. REST endpoints are generally available for historical data, while live data requires an active session and, in some cases, paid OpenF1 access.
How to install
Prerequisites:
- Git
- Node.js (LTS version) and npm
- Basic CLI environment (bash/zsh or PowerShell)
- Clone the repository:
git clone https://github.com/Panth1823/formula1-mcp
cd formula1-mcp
- Install dependencies:
npm install
- Build the project:
npm run build
- Run the MCP server (example):
# Ensure you are in the project root and the build/index.js path exists
node build/index.js
- Update your Claude/CLAUDE_DESKTOP config with the provided mcp_config snippet (see documentation in this repo) to enable the Formula1 MCP server within your MCP client.
Additional notes
Notes and tips:
- Historical data is free; live streaming and real-time data require paid OpenF1 access. REST endpoints may work during race weekends for delayed data even without a paid account.
- Live data tools: getLiveCarData, getLivePositions, getLiveWeather, getLiveRaceControl, getLiveTeamRadio, getStreamingStatus. Some data sources are MQTT-based (live) with fallback to REST.
- Before using historical tools, you may need to call getHistoricalSessions to discover session keys for specific races.
- If you encounter path or build errors, ensure the built output exists at <repo>/build/index.js and that your mcp_config points to that file.
- The MQTT streaming endpoint for live data is currently disabled in the public configuration; enable access via OpenF1 if you have a paid account and update environment/config accordingly.
Related MCP Servers
gemini-cli
An open-source AI agent that brings the power of Gemini directly into your terminal.
crawlbase
Crawlbase MCP Server connects AI agents and LLMs with real-time web data. It powers Claude, Cursor, and Windsurf integrations with battle-tested web scraping, JavaScript rendering, and anti-bot protection enabling structured, live data inside your AI workflows.
mcp -js
MCP server that exposes YepCode processes as callable tools for AI platforms. Securely connect AI assistants to your YepCode workflows, APIs, and automations.
mcpresso
TypeScript framework to build robust, agent-ready MCP servers around your APIs.
akyn-sdk
Turn any data source into an MCP server in 5 minutes. Build AI-agents-ready knowledge bases.
myinstants
MCP server that lets your ai agent press sound buttons. it's not that deep.