get_session_dataLABSCO SUMMARY
Read the model assumptions before you quote a number.
The driver analysis is built on a stated 88%/12% car-versus-driver split and the weather forecast on an LSTM/CNN ensemble — those are modelling choices, not measurements, and the answers inherit them. Where the server is unambiguously useful is the comparison work: fuel-corrected lap times and 25 mini-sector splits are exactly the transformations that make two stints comparable, and doing them by hand is the tedious part.
What it is
A Formula 1 analytics server. It pulls session data for a given year, round and session type, then layers analysis on top: tire degradation curves, fuel-corrected lap times, weather forecasting for strategy, and Monte Carlo simulation of pit strategies.
What you get
get_session_datafor a race weekend, takingyear,roundandsession— Practice 1-3, Qualifying, Sprint or Raceanalyze_tire_performancereturns degradation curves, grip-loss patterns and optimal stint lengths, filterable bydriverandcompoundanalyze_lap_timesapplies fuel correction and breaks the lap into 25 mini-sectorssimulate_race_strategyruns Monte Carlo overstrategy_options— thesimulationsargument defaults to 10,000predict_weather_impactforecasts over aforecast_hourswindow, default 3analyze_driver_performanceseparates driver from car and can compare against acomparison_driverget_real_time_telemetryandanalyze_sector_performancework over channels includingSpeed,Throttle,Brake,DRS,Gear,RPM,TireTemp,BrakeTemp,GPSandEngineTemp- Live-season tools —
get_current_season_info,get_race_schedule,connect_live_timing,get_live_timing_status,get_api_status
Requirements
Node.js 18.0.0 or higher and npm. Published as f1-mcp-server version 2.0.0; the documented path is clone, npm install, then point your client's command at node and its args at the absolute path of index.js. No API key is listed. Data comes from F1 Live Timing, the OpenF1 API and the Ergast API, with simulation as the fallback; coverage runs 2018-2025 and round numbers 1-24.
Setup effort
Build from source — git clone https://github.com/stagsz/F1-MCP-Server
USE CASES
01
Working out why a stint fell away
Pull degradation for one driver on one compound and see where grip loss started rather than eyeballing lap times.
02
Comparing two drivers fairly
Correct for fuel load first, then read the mini-sector breakdown to see where the time actually went.
03
Arguing about one-stop versus two
Simulate the candidate strategies and get probabilistic outcomes with pit windows instead of a single answer.
04
Checking whether the data source is up
Ask for the status of the upstream F1 feeds before blaming an empty result on the analysis.
13 tools
Listed in project docs. Your client may show a different list.
analyze_tire_performanceanalyze_lap_timespredict_weather_impactsimulate_race_strategyanalyze_driver_performanceget_real_time_telemetryanalyze_sector_performanceget_current_season_infoget_race_scheduleconnect_live_timingget_live_timing_statusget_api_statusBEFORE YOU INSTALL
What to know first
Tools you get
13 tools named in the project's documentation.
Requires
- node on PATH
- Node.js 18.0.0 or later
- npm
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
git clone https://github.com/stagsz/F1-MCP-Server
cd F1-MCP-Server
npm installMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"f1-mcp-server": {
"command": "node",
"args": [
"<YOUR_PATH_TO_F1_MCP_SERVER>/index.js"
],
"env": {
"NODE_ENV": "production"
}
}
}
}<YOUR_PATH_TO_F1_MCP_SERVER>/index.js is the absolute path to index.js in your clone — for example /home/username/F1-MCP-Server/index.js, or C:\Users\YourName\F1-MCP-Server\index.js on Windows.
