Skip to main content

MCP server for Formula 1 data - provides F1 telemetry, race results, standings, and analytics for Claude Desktop

Project description

F1 MCP Server

A Model Context Protocol (MCP) server that provides comprehensive Formula 1 data and analytics for Claude Desktop integration.

Features

This server exposes 36+ tools for accessing F1 data:

Race Data

  • Race results and classifications
  • Sprint race results
  • Qualifying progression (Q1, Q2, Q3)
  • Grid vs finish comparisons
  • DNF lists and retirement reasons

Telemetry & Analysis

  • Speed trace comparisons between drivers
  • Gear shift visualizations
  • Brake and throttle analysis
  • RPM and engine data
  • DRS usage patterns

Timing & Laps

  • Fastest lap data with sector times
  • Lap-by-lap timing
  • Deleted laps (track limits)
  • Lap consistency statistics
  • Personal best laps

Strategy

  • Tire compound analysis
  • Stint breakdowns
  • Pit stop data and fastest stops
  • Starting tire choices
  • Strategy comparisons

Standings & History

  • Driver championship standings
  • Constructor standings
  • Historical race winners
  • Track records

Live Data

  • Live session status
  • Real-time positions
  • Live lap times
  • Live telemetry
  • Current weather conditions

Other

  • Team radio links
  • Race control messages
  • Track status (flags, safety car)
  • Weather data
  • Circuit information

Installation

Prerequisites

  • Python 3.10 or higher
  • Claude Desktop

Setup

  1. Clone this repository:
git clone https://github.com/drivenrajat/f1.git
cd f1
  1. Create a virtual environment:
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate
  1. Install dependencies:
pip install -e .

Configure Claude Desktop

Add this server to your Claude Desktop MCP configuration (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

{
  "mcpServers": {
    "f1": {
      "command": "python",
      "args": ["/path/to/f1/f1_server.py"]
    }
  }
}

Or if using uv:

{
  "mcpServers": {
    "f1": {
      "command": "uv",
      "args": ["run", "--directory", "/path/to/f1", "python", "f1_server.py"]
    }
  }
}

Usage

Once configured, you can ask Claude questions like:

  • "Show me the 2024 F1 calendar"
  • "Get the race results from Monaco 2024"
  • "Compare telemetry between Verstappen and Norris at Silverstone qualifying"
  • "What was Hamilton's tire strategy at Spa?"
  • "Show me the current driver standings"
  • "Get the fastest pit stops from the Italian GP"

Data Sources

  • FastF1: Historical telemetry, lap times, and session data
  • Ergast API: Championship standings and historical results
  • OpenF1 API: Team radio recordings

Caching

The server automatically caches FastF1 data in a cache directory to improve performance on repeated queries.

License

MIT License - see LICENSE for details.

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

f1_mcp-0.1.0.tar.gz (30.6 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

f1_mcp-0.1.0-py3-none-any.whl (30.8 MB view details)

Uploaded Python 3

File details

Details for the file f1_mcp-0.1.0.tar.gz.

File metadata

  • Download URL: f1_mcp-0.1.0.tar.gz
  • Upload date:
  • Size: 30.6 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.5

File hashes

Hashes for f1_mcp-0.1.0.tar.gz
Algorithm Hash digest
SHA256 0cbe214868e40a94db48d45886daf7b127ecb35385f2a38a9dcd5fb9832e925d
MD5 f1795c66c6f8d8921fa68627f0408428
BLAKE2b-256 53fc7694bf1ef3a7ff42e19aed33c2525bf643ac7d1319a6c676c331840abd2b

See more details on using hashes here.

File details

Details for the file f1_mcp-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: f1_mcp-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 30.8 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.5

File hashes

Hashes for f1_mcp-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 c671acb92b0b128d069f83ad0e9959d25c2192d8236f385b1385ae1e585f10e2
MD5 f072bb8a334defbcddab714fcbc7c1c0
BLAKE2b-256 adcfea6d4ac3a3c803669ab6b856b4dc78db9f5a12e175ee8e295551389f5a87

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page