Provides real-time, historical, and news data for Formula 1 through 11 specialized tools for AI clients.
Also known as praneethravuri/pitstop, pitstop-f1
- Stars
- 1
- Tools
- 11
- Downloads, 30 days
- 65
- Latest version
- 0.5.0
- Last commit
- Nov 14, 2026
- License
- MIT
What is Pitstop MCP?
Pitstop provides real-time, historical, and news data for Formula 1 through 11 specialized tools for AI clients. It exposes 11 tools, such as get_session_data, get_telemetry_data, get_live_data.
Summary generated from the project's README
About Pitstop MCP server
Analyzing Formula 1 telemetry, race results, and news from within an AI client is what pitstop enables. This MCP server aggregates data from multiple authoritative sources like FastF1, OpenF1, and Wikidata to provide 11 specialized tools for racing enthusiasts and developers. It covers everything from real-time live intervals and pit stops to historical championship standings dating back to 1950.
Users can deploy this server via a hosted HTTP endpoint on Hugging Face or install it locally using stdio through uvx. It supports various environments including Claude Desktop, Cursor, Windsurf, and VS Code. For those needing a full local setup, it can be run via Docker to include the internal SQLite database. The server manages complex tasks like pagination, retries, and concurrency limits automatically to ensure reliable data retrieval.
What you can do with it
- 1Analyze driver performanceRequest a detailed analysis of a driver's pace, tire degradation, and stint consistency during a specific Grand Prix.
- 2Monitor live race dataTrack real-time race intervals, pit stops, and team radio updates during a live session.
- 3Retrieve historical telemetryExamine lap-by-lap car telemetry including speed, throttle, and gear changes for specific drivers.
- 4Query biographical factsUse SPARQL queries to find specific biographical information or career records for Formula 1 drivers.
Written from the project's README. Every use case is checked against a quote from it.
How to install Pitstop MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Pitstop MCP in Claude Code
$ claude mcp add --env 'PITSTOP_TRANSPORT=<PITSTOP_TRANSPORT>' pitstop -- uvx pitstop-f1Install Pitstop MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"pitstop": {
"command": "uvx",
"args": [
"pitstop-f1"
],
"env": {
"PITSTOP_TRANSPORT": "<PITSTOP_TRANSPORT>"
}
}
}
}Install Pitstop MCP in VS Code
.vscode/mcp.json
{
"servers": {
"pitstop": {
"type": "stdio",
"command": "uvx",
"args": [
"pitstop-f1"
],
"env": {
"PITSTOP_TRANSPORT": "<PITSTOP_TRANSPORT>"
}
}
}
}Install Pitstop MCP in VS Code CLI
$ code --add-mcp '{"name":"pitstop","type":"stdio","command":"uvx","args":["pitstop-f1"],"env":{"PITSTOP_TRANSPORT":"<PITSTOP_TRANSPORT>"}}'Install Pitstop MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"pitstop": {
"command": "uvx",
"args": [
"pitstop-f1"
],
"env": {
"PITSTOP_TRANSPORT": "<PITSTOP_TRANSPORT>"
}
}
}
}Install Pitstop MCP in Codex
$ codex mcp add pitstop --env 'PITSTOP_TRANSPORT=<PITSTOP_TRANSPORT>' -- uvx pitstop-f1Install Pitstop MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.pitstop] command = "uvx" args = ["pitstop-f1"] [mcp_servers.pitstop.env] PITSTOP_TRANSPORT = "<PITSTOP_TRANSPORT>"
Install Pitstop MCP in Gemini CLI
$ gemini mcp add -s user -e 'PITSTOP_TRANSPORT=<PITSTOP_TRANSPORT>' pitstop uvx -- pitstop-f1Install Pitstop MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"pitstop": {
"command": "uvx",
"args": [
"pitstop-f1"
],
"env": {
"PITSTOP_TRANSPORT": "<PITSTOP_TRANSPORT>"
}
}
}
}Pitstop MCP tools 11
Detected from the READMEget_session_dataget_telemetry_dataget_live_dataget_standingsget_scheduleget_reference_dataget_f1_newsget_resultsget_race_analysisquery_wikidataquery_f1_database
| get_session_data | — | |
| get_telemetry_data | — | |
| get_live_data | — | |
| get_standings | — | |
| get_schedule | — | |
| get_reference_data | — | |
| get_f1_news | — | |
| get_results | — | |
| get_race_analysis | — | |
| query_wikidata | — | |
| query_f1_database | — |
Configuration
PITSTOP_TRANSPORTRequiredTransport mode; must be 'stdio' when run via an MCP client.
| Name | Description | |
|---|---|---|
| PITSTOP_TRANSPORT | Transport mode; must be 'stdio' when run via an MCP client. | Required |
Automated checks
Ran Nov 12, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablePass
- Open source license (OSI)Pass
- Commit or release in the last yearPass
- Package name not close to a popular packagePass
- Remote endpoint uses HTTPSNot checked
- Destructive tools are labelledPass
- No hidden instructions to the modelPass
- No critical advisory in the package or its dependenciesPass
README
View on GitHubPitstop — F1 MCP Server
An HTTP-first Model Context Protocol (MCP) server for Formula 1 data. Aggregates real-time, historical, and news data from multiple authoritative sources into 11 tools ready for any MCP client.
v0.5.0 | Author: Praneeth Ravuri
Install
Hosted endpoint (nothing to install)
A free public instance runs on Hugging Face Spaces:
https://praneeth1025-pitstop.hf.space/mcp
claude mcp add --transport http pitstop https://praneeth1025-pitstop.hf.space/mcp
Note: the Space sleeps after long inactivity — the first request after a quiet spell takes a cold start.
Local install
stdio, via uvx (no clone needed):
PITSTOP_TRANSPORT=stdio uvx pitstop-f1
claude mcp add pitstop -e PITSTOP_TRANSPORT=stdio -- uvx pitstop-f1
codex mcp add pitstop --env PITSTOP_TRANSPORT=stdio -- uvx pitstop-f1
gemini mcp add pitstop uvx pitstop-f1 --env PITSTOP_TRANSPORT=stdio
VS Code:
code --add-mcp '{"name":"pitstop","command":"uvx","args":["pitstop-f1"],"env":{"PITSTOP_TRANSPORT":"stdio"}}'
Claude Desktop (claude_desktop_config.json), Cursor (~/.cursor/mcp.json), and Windsurf (~/.codeium/windsurf/mcp_config.json) share the same JSON shape:
{
"mcpServers": {
"pitstop": {
"command": "uvx",
"args": ["pitstop-f1"],
"env": { "PITSTOP_TRANSPORT": "stdio" }
}
}
}
Docker (HTTP transport, runs the full server incl. the F1 database):
docker compose up
# → http://localhost:8000/mcp
Overview
Pitstop exposes F1 data as 11 MCP tools over HTTP (default) or stdio. It pulls from FastF1, Jolpica, OpenF1, Wikidata, RSS feeds, and its own seeded F1 database, handling pagination, retries, caching, and concurrency limits transparently.
Data Sources
| Source | Coverage | Type |
|---|---|---|
| FastF1 | 2018–present | Historical / timing / telemetry |
| Jolpica-F1 | 1950–present | Historical (Ergast-compatible) |
| OpenF1 | 2023–present | Real-time |
| Wikidata | All eras | SPARQL queries |
| RSS Feeds (20 sources) | Live | News |
| Pitstop F1 Database | 1950–present | Owned sqlite (seeded from F1DB, self-updated weekly from Jolpica) + per-lap times |
Database refresh: .github/workflows/db-update.yml runs weekly to pull new Jolpica results into the owned F1 database.
Tools
| Tool | Description | Key Parameters |
|---|---|---|
get_session_data |
Race/qualifying results, lap times, weather, driver details (2018–present) | year, gp, session, includes, page, page_size |
get_telemetry_data |
Lap-by-lap car telemetry (speed, throttle, brake, gears) (2018–present) | year, gp, session, drivers, lap_numbers, max_points, page, page_size |
get_live_data |
Live intervals, pit stops, team radio, stints, race control, weather, position, laps, overtakes (2023–present) | data_types, year, country, session_name, driver_number, compound, flag, category, page, page_size |
get_standings |
Driver and constructor championship standings (1950–present) | year, round, type, driver_name, team_name, page, page_size |
get_schedule |
Race calendar and session schedule | year, include_testing, round, event_name, only_remaining, page, page_size |
get_reference_data |
Circuits, drivers, constructors encyclopedia (1950–present) | reference_type, year, name, page, page_size |
get_f1_news |
F1 headlines from 20 RSS sources | source, limit, keywords, driver, team, circuit, year, date_from, date_to, page, page_size |
get_results |
Race/qualifying/sprint results, lap times, pit stops (1950–present) | year, round, result_type, driver, page |
get_race_analysis |
Pace, tire degradation, stint summaries, consistency (2018–present) | year, gp, session, drivers, analysis_type, page |
query_wikidata |
SPARQL queries to Wikidata for F1 biography, career records, history | sparql, page, page_size |
query_f1_database |
Read-only SQL over pitstop's owned F1 database (1950–present): results, standings, driver family trees, team lineage | sql, page, page_size |
Transport
HTTP (default)
uv sync
uv run pitstop
# → http://localhost:8000
MCP client config:
{
"mcpServers": {
"pitstop": {
"type": "http",
"url": "http://localhost:8000/mcp"
}
}
}
stdio (opt-in)
PITSTOP_TRANSPORT=stdio uv run pitstop
MCP client config:
{
"mcpServers": {
"pitstop": {
"command": "uv",
"args": ["run", "--directory", "/path/to/pitstop", "pitstop"],
"env": { "PITSTOP_TRANSPORT": "stdio" }
}
}
}
Health API
| Endpoint | Purpose |
|---|---|
GET /health |
Per-source status (FastF1, f1db, Jolpica, OpenF1, RSS) |
GET /live |
Liveness probe |
GET /ready |
Readiness probe |
Example /health response:
{
"version": "0.5.0",
"overall": "ok",
"sources": [
{ "name": "fastf1", "status": "ok", "latency_ms": 2, "detail": "cache writable" },
{ "name": "f1db", "status": "ok", "latency_ms": 1, "detail": "" },
{ "name": "jolpica", "status": "ok", "latency_ms": 134, "detail": "" },
{ "name": "openf1", "status": "ok", "latency_ms": 98, "detail": "" },
{ "name": "rss", "status": "ok", "latency_ms": 210, "detail": "" }
]
}
overall is "ok" / "degraded" / "down". HTTP 200 / 207 / 503.
Wikidata SPARQL
query_wikidata runs SPARQL queries against Wikidata for biographical and historical F1 facts not covered by race APIs.
Only SELECT and ASK queries are accepted (read-only). Always include LIMIT in your query.
Example — find F1 drivers with their birthdate:
SELECT ?driver ?driverLabel ?birthDate WHERE {
?driver wdt:P31 wd:Q5 ;
wdt:P641 wd:Q1968 ;
wdt:P569 ?birthDate .
SERVICE wikibase:label { bd:serviceParam wikibase:language "en" }
} ORDER BY DESC(?birthDate) LIMIT 10
Pagination
All list-returning tools accept page (1-based, default 1) and page_size (defaults vary per tool: 10–50). Responses include a pagination block:
{
"data": [...],
"pagination": {
"page": 1,
"page_size": 20,
"total_items": 47,
"total_pages": 3,
"has_next": true,
"has_prev": false
}
}
Configuration
| Variable | Default | Description |
|---|---|---|
PITSTOP_TRANSPORT |
http |
http or stdio |
PITSTOP_HOST |
0.0.0.0 |
Bind address (HTTP only) |
PITSTOP_PORT |
8000 |
Listen port (HTTP only) |
PITSTOP_ENV |
development |
development or production |
PITSTOP_LOG_LEVEL |
Depends on PITSTOP_ENV |
DEBUG if development, else INFO |
PITSTOP_LOG_FORMAT |
Depends on PITSTOP_ENV |
text if development, else json |
PITSTOP_ENABLE_CACHING |
true |
Enable HTTP response and FastF1 disk caching |
PITSTOP_CACHE_TTL_SECONDS |
300 |
HTTP response cache time-to-live (seconds) |
PITSTOP_RATE_LIMIT_ENABLED |
false |
Enable concurrent-call limiting |
PITSTOP_RATE_LIMIT_PER_HOUR |
3600 |
Max concurrent calls (derived from per-hour quota) |
FASTF1_CACHE |
cache |
FastF1 cache directory path |
Caching
Pitstop uses in-memory HTTP response caching (via Hishel) for GET requests with 200 responses. This keeps tool calls inside upstream rate limits:
- Jolpica: 4 req/s, 500/hr
- OpenF1: 3 req/s, 30/min
- Wikidata: Query complexity limits
- RSS: Per-feed redirects cached
FastF1 maintains its own disk cache in FASTF1_CACHE directory. Control caching via:
PITSTOP_ENABLE_CACHING=true(default)PITSTOP_CACHE_TTL_SECONDS=300(default)
Development
uv sync --dev
uv run pytest
uv run ruff check src/
Contributing
See CONTRIBUTING.md.
Credits & attribution
| Source | Description | License |
|---|---|---|
| F1DB | Database seeded from F1DB and subsequently modified & extended by pitstop | CC BY 4.0 |
| FastF1 | Python library for F1 timing, telemetry, and session data | MIT |
| Jolpica-F1 | Ergast-compatible F1 data API, 1950–present; also used to self-update the F1DB-seeded database weekly | — |
| OpenF1 | Free open-source API for real-time F1 data | MIT |
| Wikidata | Open knowledge graph with SPARQL query service | CC0 |
| Ergast Motor Racing API | Historical F1 data 1950–2024 (now served via Jolpica) | — |
| RSS Feeds (20 sources) | News headlines, credited collectively; see each feed's link field in get_f1_news results |
Respective publishers |
Not affiliated with Formula 1 or the FIA. Data provided by third-party sources under their respective terms.
Pitstop MCP questions
How do I add Pitstop MCP to Claude Code?
Run claude mcp add --env 'PITSTOP_TRANSPORT=<PITSTOP_TRANSPORT>' pitstop -- uvx pitstop-f1 in your terminal. Add --scope user to make it available in every project.
How do I add Pitstop MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does Pitstop MCP provide?
It exposes 11 tools, including get_session_data, get_telemetry_data, get_live_data, get_standings, get_schedule.
How can I install Pitstop locally?
You can install it via stdio using uvx by running PITSTOP_TRANSPORT=stdio uvx pitstop-f1.
Does Pitstop provide real-time data?
Yes, it includes live intervals, pit stops, team radio, and race control data through the get_live_data tool.
Can I run SPARQL queries for F1 history?
Yes, the query_wikidata tool allows you to run read-only SELECT and ASK SPARQL queries against Wikidata for biographical and historical facts.