MCP-F1
Documentation
F1 MCP Server
A Model Context Protocol (MCP) server that provides Formula 1 data using the FastF1 Python package.
Features
- Get race schedules for any F1 season
- Retrieve session results (practice, qualifying, race)
- Access lap times and telemetry data
- Driver and constructor standings
- Circuit information
Quick Start
Prerequisites
- Python 3.13
- uv package manager
1. Install uv (if not already installed)
# macOS/Linux
curl -LsSf https://astral.sh/uv/install.sh | sh
# Windows
powershell -c "irm https://astral.sh/uv/install.ps1 | iex"2. Setup F1 MCP Server
# Quick setup
./quick-start.sh
# Or manually
make install
# or: uv sync && uv pip install -e .3. Run the server
# MCP mode (for MCP Inspector)
make mcp
# HTTP mode (for OAuth testing)
make http
# With MCP Inspector
make inspectorMCP Inspector Setup
The MCP Inspector is a powerful tool for testing and debugging MCP servers. Here's how to set it up:
1. Install Node.js (if not already installed)
# macOS with Homebrew
brew install node
# Or download from https://nodejs.org/2. Install MCP Inspector
# Install globally with npm
npm install -g @modelcontextprotocol/inspector
# Verify installation
mcp-inspector --version3. Run F1 MCP Server with Inspector
# Using make command (recommended)
make inspector
# Or manually
mcp-inspector uv run python -m f1_mcp_server.server4. Using MCP Inspector
Once started, the inspector will:
1. Launch a web interface (usually at `http://localhost:5173`)
2. Connect to your F1 MCP server automatically
3. Provide an interactive UI to test all available tools
Available F1 Tools in Inspector:
- `get_race_schedule` - Browse F1 race calendars
- `get_session_results` - View race/qualifying results
- `get_driver_standings` - Check championship standings
- `get_constructor_standings` - Team championship data
- `get_lap_times` - Detailed lap timing analysis
5. Example Usage in Inspector
Try these sample requests in the MCP Inspector:
Get 2024 Race Schedule:
{
"year": 2024
}Get Monaco GP Race Results:
{
"year": 2024,
"round_number": 8,
"session": "R"
}Get Lap Times for Verstappen:
{
"year": 2024,
"round_number": 1,
"session": "R",
"driver": "VER"
}Troubleshooting MCP Inspector
Inspector won't start:
# Check Node.js version (needs 16+)
node --version
# Reinstall inspector
npm uninstall -g @modelcontextprotocol/inspector
npm install -g @modelcontextprotocol/inspectorServer connection issues:
# Test server directly first
make test-startup
# Check if server starts without inspector
make mcpPort conflicts:
# Inspector uses port 5173 by default
# Kill any processes using the port
lsof -ti:5173 | xargs kill -9Usage with MCP Inspector
The MCP Inspector provides a web-based interface for testing F1 data tools:
# Install MCP Inspector (requires Node.js)
npm install -g @modelcontextprotocol/inspector
# Run F1 server with inspector
make inspector
# Or manually
mcp-inspector uv run python -m f1_mcp_server.serverInspector Features:
- Interactive web UI at `http://localhost:5173`
- Real-time F1 data testing
- JSON schema validation
- Tool documentation browser
Available Tools
- `get_race_schedule`: Get the race schedule for a specific season
- `get_session_results`: Get results for a specific session
- `get_driver_standings`: Get driver championship standings
- `get_constructor_standings`: Get constructor championship standings
- `get_lap_times`: Get lap times for a specific session
Frequently asked questions
What is MCP-F1?
MCP-F1 is a Model Context Protocol (MCP) server listed in the TrackMCP directory.
How do I install MCP-F1?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is MCP-F1 open source?
Yes — it is hosted on GitHub at https://github.com/josh-mantel/mcp-f1.
Related MCP tools
5. Update .env file in the root directory with your mem0 API key: for the Model Context Protocol. Enhance AI assistants with powerful integrations.
Model Context Protocol integration for Python. Enhance AI assistants with powerful Python-based capabilities and integration support.
This repository contains Model Context Protocol (MCP) servers that enable MCP clients (like Claude Desktop or the cline.
🙌 OpenHands: Code Less, Make More for the Model Context Protocol. Enhance AI assistants with powerful integrations. Python-based implementation.
Universal memory layer for AI Agents; Announcing OpenMemory MCP - local and secure memory management. Python-based implementation.
基于大模型搭建的聊天机器人,同时支持 微信公众号、企业微信应用、飞书、钉钉 等接入,可选择ChatGPT/Claude/DeepSeek/文心一言/讯飞星火/通义千问/ Gemini/GLM-4/Kimi/LinkAI,能处理文本、语音和图片,访问操作系统和互联网,支持基于自有知识库进行定制企业智能客服。
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP