Provides a web interface built with Gradio to explore Formula 1 statistics and data, including championship standings, event information, and session results.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Formula 1 MCP Server Show me the 2023 driver championship standings"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
This project defines a MCP server for Formula 1 data, providing fans, analysts, and developers with easy access to a vast range of F1 statistics and information. Built with Python and powered by the Gradio framework, it offers a user-friendly web interface to explore historical and recent F1 data from the FastF1 library and the official OpenF1 API.
Related MCP server: Pitstop
Architectural overview of the MCP server and client. The MCP server is hosted using a Gradio back-end and can be either run locally or on a remote server.
The interface is organized into several Gradio tabs, each dedicated to a specific type of F1 data:
Championship Standings: View final driver and constructor championship standings for any season from 1950 to the present.
Event Information: Get detailed information for any Grand Prix, including schedules and circuit details.
Season Calendar: Display the complete race calendar for a given year.
Track Visualizations: Generate and view plots of the fastest race lap, visualizing speed, gear changes, and cornering G-forces.
Session Results: Fetch detailed results for any race session (Practice, Qualifying, or Race).
Driver & Constructor Info: Look up background information and statistics for drivers and teams.
OpenF1 API Tools: An advanced toolkit for developers to directly query the OpenF1 API, build custom requests, and view raw JSON responses.
Backend: Python
Web Framework: Gradio
Data Sources:
fastf1 Python library for historical data.
openf1 for live and recent data via their public API.
Key Libraries: pandas, matplotlib
The MCP server is defined inside app.py.
The MCP client and AI agent is defined inside mcp_client.py and allows interaction with the MCP server through server side events (SSE) transport.
For MCP clients that support SSE transport (for Claude Desktop, see below), the following configuration can be used:
{
"mcpServers": {
"gradio": {
"url": "https://agents-mcp-hackathon-f1-mcp-server.hf.space/gradio_api/mcp/sse"
}
}
}For Claude Desktop, the following configuration can instead be used, but make sure you have Node.js installed:
{
"mcpServers": {
"gradio": {
"command": "npx",
"args": [
"mcp-remote",
"https://agents-mcp-hackathon-f1-mcp-server.hf.space/gradio_api/mcp/sse",
"--transport",
"sse-only"
]
}
}
}Apply one or more filter strings to an API endpoint URL.
Inputs: param_1, api_string.
Get the championship standing for a specific constructor in a given year.
Inputs: year, constructor_name.
Get the championship standing for a specific driver in a given year.
Inputs: year, driver_name.
Retrieve the API endpoint URL and filter metadata for a given OpenF1 endpoint.
Inputs: endpoint.
Retrieve a list of all available OpenF1 API endpoints. Returns: dict: A dictionary containing a single key 'endpoints' with a list of available endpoint names as strings.
Inputs: no named parameters.
Retrieve detailed information about a specific constructor.
Inputs: constructor_name.
Retrieve detailed information about a specific driver.
Inputs: driver_name.
Retrieve detailed information about a specific OpenF1 API endpoint.
Inputs: endpoint.
Retrieve information about a specific Formula 1 event.
Inputs: year, round, format.
Retrieve detailed information about a specific OpenF1 API filter.
Inputs: filter_name.
Create a filter string for OpenF1 API requests.
Inputs: operator, filter_name, filter_value.
Get the complete race calendar for a specific F1 season.
Inputs: year.
Retrieve and format the results of a specific session.
Inputs: year, round, session_type.
Send an HTTP GET request to the specified API endpoint and return the JSON response.
Inputs: api_string.
Generate a visualization of the track with specified data.
Inputs: year, round, visualization_type.
Inputs: year.
Inputs: year.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 17 tools
Core F1 retrieval tools (standings, event info, session results, driver/constructor info) are clearly distinct. However, the OpenF1 API plumbing tools (get_api_endpoints, get_api_endpoint, get_endpoint_info, get_filter_info, get_filter_string, apply_filters, send_request) overlap heavily in purpose, and update_drivers/update_constructors have no descriptions, making their boundaries unclear.
All tools share a consistent f1_mcp_server_ prefix and mostly use verb_noun or verb_resource naming (get_*, update_*). Minor deviations exist: championship_standings and track_visualization lack explicit verbs, and get_api_endpoint vs get_api_endpoints differ only by plural.
17 tools is on the heavy side for an F1 data server. While core domain tools are justified, seven generic OpenF1 API access/filter tools appear to expose implementation plumbing rather than distinct user-facing capabilities, inflating the count.
The surface covers key F1 entities (drivers, constructors, standings, events, calendars, session results) and generic OpenF1 request tools provide fallback access to unmodeled data like laps, telemetry, or pit stops. Explicit list/search tools and clear update semantics are missing, but agents can work around most gaps.
Anonymous read-only Formula 1 tools, resources, prompts, completion, and interactive dashboard.
Read-only F1 game laps, telemetry, setups, leaderboard benchmarks, and progress.
