Grand Prix Data Gateway (F1 MCP Service)

An implementation of the Model Context Protocol (MCP) dedicated to serving Formula One racing data. This package furnishes numerous utilities for interrogating F1 datasets, including event agendas, participant biographicals, intricate telemetry logs, and finalized competition results.

Key Capabilities

• Event Chronology: Retrieval of the complete F1 contest calendar across selectable seasons.
• Event Specifics: Acquisition of in-depth data pertaining to singular Grand Prix meetings.
• Session Outcomes: Comprehensive result sets derived from races, qualification periods, sprint contests, and practice runs.
• Competitor Profiling: Access to detailed driver attributes relevant to specific race segments.
• Performance Deep Dive: Statistical examination of a driver's efficiency, focusing on lap timing metrics.
• Driver Benchmarking: Ability to juxtapose operational metrics between several drivers within the identical session context.
• Telemetry Acquisition: Retrieval of high-granularity telemetry information tied to individual laps.
• Championship Tracking: Current and historical views of both driver and constructor standings for any given year.

Deployment

Installation via Smithery

For automated deployment into Claude Desktop environments using Smithery:

bash npx -y @smithery/cli install @Machine-To-Machine/f1-mcp-server --client claude

Conventional Python Setup

In a project managed by uv, incorporate this package into dependencies via:

bash uv add f1-mcp-server

Alternatively, for environments utilizing pip for dependency resolution: bash pip install f1-mcp-server

To initiate the server within your current project context:

bash uv run f1-mcp-server

Or to launch globally within an isolated execution space:

bash uvx f1-mcp-server

For direct installation from the source repository:

bash git clone https://github.com/Machine-To-Machine/f1-mcp-server.git cd f1-mcp-server pip install -e .

Operational Modes

Interface Execution

The server can be invoked in two primary configurations:

Standard Stream Mode (the default):

bash uvx run f1-mcp-server

Server-Sent Events (SSE) Transport Mode (optimized for web frontends):

bash uvx f1-mcp-server --transport sse --port 8000

Programmatic Interface (Python)

python from f1_mcp_server import main

Execute the server utilizing default parameters

main()

Or configure with specific SSE transport parameters

main(port=9000, transport="sse")

Exposed API Toolkit

The server furnishes the following capabilities through the MCP interface:

Method Identifier	Functional Description
get_event_schedule	Retrieve the Formula One racing calendar pertinent to a specified year.
get_event_info	Obtain granular details concerning an individual Formula One Grand Prix.
get_session_results	Fetch finalized outcomes for any designated Formula One competition segment.
get_driver_info	Secure biographical and session-specific data for a particular Formula One participant.
analyze_driver_performance	Conduct in-depth evaluation of a driver's efficiency across a Formula One session.
compare_drivers	Execute a comparative analysis of performance metrics between multiple Formula One racers.
get_telemetry	Access high-fidelity telemetry streams recorded for a selected Formula One lap.
get_championship_standings	Query the current status of Formula One driver and constructor championship rankings.

Consult the FastF1 Documentation for comprehensive details regarding the underlying data sourcing mechanisms:

Required Packages

• anyio (>=4.9.0)
• click (>=8.1.8)
• fastf1 (>=3.5.3)
• mcp (>=1.6.0)
• numpy (>=2.2.4)
• pandas (>=2.2.3)
• uvicorn (>=0.34.0)

Development Workflow

Environment Configuration

bash git clone https://github.com/Machine-To-Machine/f1-mcp-server.git cd f1-mcp-server uv venv source .venv/bin/activate # Windows equivalent: .venv\Scripts\activate uv pip install -e ".[dev]"

Quality Assurance Checks

bash

Execute static analysis checks (linting)

uv run ruff check .

Validate code formatting adherence

uv run ruff format --check .

Perform security vulnerability scanning

uv run bandit -r src/

Contribution Protocol

1. Duplicate the repository (Fork).
2. Establish a dedicated feature branch: git checkout -b new-feature-name
3. Commit modifications: git commit -am 'Implementing requested enhancement'
4. Push the branch to the upstream remote: git push origin new-feature-name
5. Submit a formal Pull Request.

Licensing

This software is distributed under the terms specified in the MIT License (refer to the LICENSE file for full details).

Originators

• Machine To Machine

Special Recognition

We extend gratitude to the creators of FastF1, a superior Python library essential for Formula 1 data retrieval. Their dedication is greatly appreciated.

This implementation drew inspiration from the TypeScript project located at rakeshgangwar/f1-mcp-server, with significant adaptation occurring in the f1_data.py module based on their original source structure.