MCP.Market

MCP Sport MCP server

by andrequeiroz2·io.github.andrequeiroz2/mcp-sport·v0.1.0·1 stars
No reviews yet

MCP server that exposes Formula 1 data from the OpenF1 API.

A88/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A88/100

full report

Adoption
New

1 stars18 downloads/wk

Reviews

Write one

Nobody has reviewed MCP Sport yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

MCP Sport tools (20)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • get_car_data

    Fetch car telemetry (speed, rpm, gear, throttle, brake, DRS) from OpenF1.

  • get_drivers

    Fetch F1 drivers from OpenF1, filtered by session, meeting or identity fields.

  • get_drivers_championship

    Fetch drivers championship standings from OpenF1 (beta endpoint).

  • get_drivers_championship_view

    Fetch drivers championship standings and render them as a visual board.

  • get_intervals

    Fetch real-time gaps between drivers and to the race leader from OpenF1.

  • get_laps
  • get_location

    Fetch approximate car positions on the circuit from OpenF1.

  • get_meetings

    Fetch F1 meetings (Grand Prix or testing weekends) from OpenF1.

  • get_overtakes

    Fetch overtakes during F1 races from OpenF1.

  • get_pit_stops

    Fetch pit lane passes for an F1 session from OpenF1.

  • get_positions

    Fetch driver position changes throughout an F1 session from OpenF1.

  • get_race_control

    Fetch race control events (flags, safety car, incidents) from OpenF1.

  • get_race_replay_view

    Replay a race as an animated position chart (bar-chart-race style).

  • get_session_results

    Fetch the final classification of an F1 session from OpenF1.

  • get_sessions

    Fetch F1 sessions (practice, qualifying, sprint, race) from OpenF1.

  • get_starting_grid

    Fetch the starting grid for an F1 race from OpenF1.

  • get_stints

    Fetch tyre stints (periods of continuous driving) from OpenF1.

  • get_team_radio

    Fetch team radio exchanges between drivers and teams from OpenF1.

  • get_teams_championship

    Fetch teams championship standings from OpenF1 (beta endpoint).

  • get_weather

    Fetch weather conditions over the track from OpenF1 (sampled every minute).

Public scan report

scanner v0.1.10 · 2026-11-01 · same rubric, same numbers if you re-run it

no findings
  • Code scan90 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 41 days ago12/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 88/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How MCP Sport compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
88/100
higher than 75% of 48,255 servers
Tools
20
the typical server has 7
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
1
more than 65% of 28,688 servers
Downloads a week
18
more than 5% of 12,191 servers with a package

What its tools let an agent do: 20 read

Install MCP Sport in Claude Code, Cursor or VS Code

claude mcp add mcp-sport -- uvx mcp-sport
Add to Cursor

What the publisher says

From the MCP Sport repository's README, as published. We do not edit it. Read it on GitHub

MCP Sport — F1 Telemetry MCP 🏎️

<!-- mcp-name: io.github.andrequeiroz2/mcp-sport -->

An MCP (Model Context Protocol) server that exposes Formula 1 data from the OpenF1 API as tools for AI assistants (Claude Desktop, Cursor, MCP Inspector, etc.).

Full coverage: 18 data tools matching the 18 documented OpenF1 endpoints — sessions, meetings, drivers, results, laps, pit stops, stints, telemetry, weather, championships and more. Two MCP App views sit on top of that data: a drivers standings board and an animated race replay. Hosts that render MCP Apps show the HTML. Cursor and Claude Desktop do not: they return the same payload as JSON.

Stack

Installation

# Clone and install dependencies
git clone https://github.com/andrequeiroz2/mcp-sport.git mcp-sport
cd mcp-sport
uv sync

Usage

Run the server (stdio)

.venv/bin/python src/mcp_sport/server.py

MCP Inspector (web UI to test the tools)

npx @modelcontextprotocol/inspector@latest .venv/bin/python src/mcp_sport/server.py

In the Inspector UI: transport STDIO, command .venv/bin/python, args src/mcpsport/server.py → Connect**.

Claude Desktop / Cursor

Add to the client's MCP configuration:

{
  "mcpServers": {
    "f1-telemetry": {
      "command": "/absolute/path/mcp-sport/.venv/bin/python",
      "args": ["/absolute/path/mcp-sport/src/mcp_sport/server.py"]
    }
  }
}

The 18 data tools work in both clients. The views do not render there.

Views (MCP Apps)

getdriverschampionshipview and getracereplayview return interactive HTML. Cursor and Claude Desktop are incompatible with MCP Apps: they ignore the UI and show the JSON payload. The MCP Inspector also treats the result as text.

The views were validated in the official basic-host from modelcontextprotocol/ext-apps. The server must be HTTP, with CORS exposing the MCP session headers. Otherwise the browser cannot complete the Streamable HTTP handshake.

Terminal 1 — MCP server on port 8765:

uv run python -c "
import uvicorn
from starlette.middleware import Middleware
from starlette.middleware.cors import CORSMiddleware
from mcp_sport.server import mcp

app = mcp.http_app(middleware=[Middleware(
    CORSMiddleware,
    allow_origins=['*'],
    allow_methods=['*'],
    allow_headers=['*'],
    expose_headers=['mcp-session-id', 'mcp-protocol-version'],
)])
uvicorn.run(app, host='127.0.0.1', port=8765)
"

Terminal 2 — basic-host (needs Node.js; npm start requires bun, so use tsx):

git clone --depth 1 https://github.com/modelcontextprotocol/ext-apps.git
cd ext-apps/examples/basic-host
npm install
npm run build
SERVERS='["http://127.0.0.1:8765/mcp"]' npx tsx serve.ts

Open http://localhost:8080 (sandbox on :8081) and call getdriverschampionshipview or getracereplayview. After a change to the view HTML, hard-refresh the page (Ctrl+Shift+R) before running the tool again. The host caches the ui:// resource.

Available tools (18)

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

MCP Sport: common questions

Is MCP Sport MCP server safe?
Yes, by our scan: it is graded A (88/100). Read the MCP Sport safety report
How do I install MCP Sport?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does MCP Sport need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is MCP Sport maintained?
The last commit was 43 days ago (2026-09-21). The latest release is v0.1.0.
How does MCP Sport compare with other MCP servers?
safety score 88/100 (higher than 75% of 48,255 servers); tools 20 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.