Skip to main content
Glama
Formula One MCP Server (Python)

Formula One MCP Server (Python)

一级方程式 MCP 服务器

PyPI 版本 Python 版本 许可证:MIT 铁匠徽章

提供一级方程式赛车数据的模型上下文协议 (MCP) 服务器。该软件包提供了各种用于查询 F1 数据的工具,包括赛事日程、车手信息、遥测数据和比赛结果。

特征

  • 赛事日程:查看任意赛季的完整 F1 赛事日程

  • 赛事信息:有关特定大奖赛赛事的详细数据

  • 比赛结果:比赛、排位赛、短跑和练习赛的综合结果

  • 驾驶员信息:访问特定会话的驾驶员详细信息

  • 性能分析:通过单圈时间统计数据分析驾驶员的表现

  • 车手对比:比较同一时段内多名车手的表现

  • 遥测数据:获取特定圈数的详细遥测数据

  • 锦标赛积分榜:查看任意赛季的车手和车队积分榜

Related MCP server: Formula One MCP Server

安装

通过 Smithery 安装

要通过Smithery自动为 Claude Desktop 安装 f1-mcp-server:

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

手动安装

在uv管理的 python 项目中,通过以下方式添加依赖项:

uv add f1-mcp-server

或者,对于使用pip作为依赖项的项目:

pip install f1-mcp-server

要在项目内运行服务器:

uv run f1-mcp-server

或者在隔离环境中全局运行它:

uvx f1-mcp-server

直接从源安装:

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

用法

命令行

该服务器可以以两种模式运行:

标准 I/O 模式(默认):

uvx run f1-mcp-server

SSE 传输模式(适用于 Web 应用程序):

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

Python API

from f1_mcp_server import main

# Run the server with default settings
main()

# Or with SSE transport settings
main(port=9000, transport="sse")

API 文档

服务器通过 MCP 公开以下工具:

工具名称

描述

get_event_schedule

获取特定赛季的一级方程式赛车赛程

get_event_info

获取有关特定一级方程式大奖赛的详细信息

get_session_results

获取特定一级方程式赛事的结果

get_driver_info

获取有关特定一级方程式赛车手的信息

analyze_driver_performance

分析一级方程式赛车比赛中车手的表现

compare_drivers

比较多名一级方程式赛车手的表现

get_telemetry

获取一级方程式赛车特定圈数的遥测数据

get_championship_standings

获取一级方程式锦标赛积分榜

有关底层数据的详细信息,请参阅 FastF1 文档: FastF1 文档

依赖项

  • anyio(>=4.9.0)

  • 点击(>=8.1.8)

  • fastf1(>=3.5.3)

  • mcp(>=1.6.0)

  • numpy(>=2.2.4)

  • 熊猫(>=2.2.3)

  • uvicorn(>=0.34.0)

发展

设置开发环境

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

代码质量

# Run linting
uv run ruff check .

# Run formatting check
uv run ruff format --check .

# Run security checks
uv run bandit -r src/

贡献指南

  1. 分叉存储库

  2. 创建功能分支: git checkout -b feature-name

  3. 提交您的更改: git commit -am 'Add some feature'

  4. 推送到分支: git push origin feature-name

  5. 提交拉取请求

执照

该项目根据 MIT 许可证获得许可 - 有关详细信息,请参阅 LICENSE 文件。

作者

  • 机器对机器

致谢

该项目利用了FastF1 ,这是一个用于访问一级方程式赛车数据的优秀 Python 包。我们感谢它的维护者和贡献者。

该项目f1_data.py灵感来源于用 TypeScript 编写的rakeshgangwar/f1-mcp-server。f1_data.py模块大部分改编自其源代码。

Available Tools

8 tools
analyze_driver_performanceC

Analyze a driver's performance in a Formula One session

Inputs: year (required), event_identifier (required), session_name (required), driver_identifier (required).

compare_driversB

Compare performance between multiple Formula One drivers

Inputs: year (required), event_identifier (required), session_name (required), drivers (required).

get_championship_standingsC

Get Formula One championship standings

Inputs: year (required), round_num.

get_driver_infoC

Get information about a specific Formula One driver

Inputs: year (required), event_identifier (required), session_name (required), driver_identifier (required).

get_event_infoB

Get detailed information about a specific Formula One Grand Prix

Inputs: year (required), identifier (required).

get_event_scheduleA

Get Formula One race calendar for a specific season

Inputs: year (required).

get_session_resultsC

Get results for a specific Formula One session

Inputs: year (required), event_identifier (required), session_name (required).

get_telemetryC

Get telemetry data for a specific Formula One lap

Inputs: year (required), event_identifier (required), session_name (required), driver_identifier (required), +1 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.5/5.0

    Scored across 8 tools

    Disambiguation5/5

    All 8 tools target distinct aspects of Formula One data—drivers, events, sessions, championships, and telemetry—with no overlapping functionality. Each has a clear, non-redundant purpose.

    Naming Consistency5/5

    Every tool uses a consistent verb_noun pattern with lowercase and underscores (e.g., get_driver_info, analyze_driver_performance). The naming is predictable and adheres to a single convention.

    Tool Count5/5

    With 8 tools, the server is well-scoped for its domain. It covers essential F1 operations without being too sparse or overly granular, making it ideal for most common queries without excessive complexity.

    Completeness4/5

    The tool set covers major areas: driver info, performance analysis, comparisons, standings, event details, schedule, session results, and telemetry. One minor gap is lack of team/constructor info, but the surface is otherwise comprehensive for a dedicated F1 server.

    Maintenance

    ActivityInactive
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Provides real-time and historical Formula 1 racing data through the Model Context Protocol, offering access to timing data, driver stats, race results, telemetry, and more.
      14
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      A Model Context Protocol server that provides comprehensive Formula One racing data, enabling access to event schedules, driver information, telemetry data, race results, and performance analytics through natural language queries.
      8
      1
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      MCP server for Formula 1 data via the FastF1 library. Ask Claude (or any MCP-compatible client) about race results, lap times, telemetry, standings, pit stops, and qualifying — with historical data back to 1950 via the Ergast API.
      21
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      A local MCP server that gives Claude (or any MCP-compatible AI client) access to Formula 1 race data. Load any session from 2018 onwards, ask questions in natural language, and get answers backed by real telemetry, timing, and strategy data.
      17
      1
      MIT