mcpbeat Sign in

WeatherXM FACT — Forecast Accuracy & Ground-Truth Verification MCP Server

by weatherxm-fact Your server? Claim it
answering

WeatherXM FACT — Forecast Accuracy & Ground-Truth Verification is answering right now. Last checked 12 min ago. It exposes 4 tools.

Scores 45 NWP & AI weather models (ECMWF, GFS, ICON, meteoblue, MOSAIC) against 8,927 stations.

Uptime history 6 days of history
6 days agonow
100.0%
Uptime 24h
91 of 91 checks
4
Tools
read from the server
216 ms
Response time
average over 24h
open, no key
Access
streamable-http

What changed 14

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 8 November 2026. No other catalogue keeps this.

9 Nov 3 tool descriptions were rewritten get_best_forecast_model, get_fact_leaderboard, get_model_head_to_head
8 Nov 4 tools changed the parameters they ask for6 times that day check_ground_truth_coverage, get_best_forecast_model, get_fact_leaderboard and 1 more
8 Nov 4 tool descriptions were rewritten5 times that day check_ground_truth_coverage, get_best_forecast_model, get_fact_leaderboard and 1 more
and 3 more, back to 8 November 2026

Nothing serious here today

Today is the operative word: we check WeatherXM FACT — Forecast Accuracy & Ground-Truth Verification every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 12 min ago.

run in your terminal
claude mcp add mcp --transport http https://fact.weatherxm.com/mcp
Settings → Connectors → Add custom connector, then paste this address
https://fact.weatherxm.com/mcp
~/.codex/config.toml
[mcp_servers.mcp]
url = "https://fact.weatherxm.com/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "mcp": {
      "url": "https://fact.weatherxm.com/mcp"
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "mcp": {
      "type": "http",
      "url": "https://fact.weatherxm.com/mcp"
    }
  }
}

Available tools 4

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

best
get_best_forecast_model
Find which weather forecast model had the lowest verified historical error (MAE) for a latitude/longitude coordinate (or station_or_report_id), weather variable (temperature, wind_speed, wind_direction, precipitation, humidity), and forecast horizon (Days 0-7). For wind_direction, errors are circular shortest-arc angular errors (0°–180°, where 359° vs 1° = 2° error) on speed-weighted hourly vector averages, returning both all-hours and >3 m/s active-wind rankings. For wind_speed the default is all hours, with an optional windier-days subset (daily mean scaled observed speed >= 3 m/s) returned separately. All 45 FACT models (2025 archive, 2025-02-13 to 2025-12-31, QoD >= 0.80 station-days): WeatherXM MOSAIC (MOSAIC), meteoblue (METEOBLUE), meteoblue station-mLM (commissioned) (mLM), ECMWF IFS (IFS025, IFSHRES), ECMWF AIFS AI (AIFS025), NOAA GFS 0.5° (GFS05), NOAA HRRR (HRRR), NOAA National Blend of Models (NBM), NOAA NAM (NAM3, NAM5, NAM12, NAMAK), DWD ICON (ICON, ICONEU, ICOND2), UK Met Office (UMGLOBAL10, UKMO2), ECCC GEM (GEM15, GEM2), Meteo-France ARPEGE/AROME (MFGLOBAL, MFEU, MFFR), COSMO (COSMOI2, COSMOM5), HARMONIE-AROME (HARMONIE), JMA MSM (MSM), WRF (WRFGR, WRFAMS), meteoblue NEMS/NMM (NEMSGLOBAL, NEMSGLOBAL_E, NEMS4, NEMS12, NEMS12_E, NEMSAF01, NEMSAS02, NEMSCAM, NEMSIN, NEMSNZ, NEMSSA, NMM4, NMM22), regional models (AF01, AS01, SA01). GFS025 is not archived; requests for it resolve to GFS05 with a resolution warning. Useful for solar & wind energy forecasting, agriculture & frost/irrigation risk, maritime/port & drone operations, construction planning, and microclimate evaluation. Provide (lat, lon) or station_or_report_id. Missing results stay unknown; not live forecasting.
fact
get_fact_leaderboard
Read the global weather forecast accuracy leaderboard (MAE, RMSE, circular angular error for wind_direction including >3 m/s active-wind curves, and categorical rain skill HSS, POD, FAR, CSI across lead days 0..7) or country-level published H3 cell-win summaries across all 45 forecast models and 8,927 stations. All 45 FACT models (2025 archive, 2025-02-13 to 2025-12-31, QoD >= 0.80 station-days): WeatherXM MOSAIC (MOSAIC), meteoblue (METEOBLUE), meteoblue station-mLM (commissioned) (mLM), ECMWF IFS (IFS025, IFSHRES), ECMWF AIFS AI (AIFS025), NOAA GFS 0.5° (GFS05), NOAA HRRR (HRRR), NOAA National Blend of Models (NBM), NOAA NAM (NAM3, NAM5, NAM12, NAMAK), DWD ICON (ICON, ICONEU, ICOND2), UK Met Office (UMGLOBAL10, UKMO2), ECCC GEM (GEM15, GEM2), Meteo-France ARPEGE/AROME (MFGLOBAL, MFEU, MFFR), COSMO (COSMOI2, COSMOM5), HARMONIE-AROME (HARMONIE), JMA MSM (MSM), WRF (WRFGR, WRFAMS), meteoblue NEMS/NMM (NEMSGLOBAL, NEMSGLOBAL_E, NEMS4, NEMS12, NEMS12_E, NEMSAF01, NEMSAS02, NEMSCAM, NEMSIN, NEMSNZ, NEMSSA, NMM4, NMM22), regional models (AF01, AS01, SA01). GFS025 is not archived; requests for it resolve to GFS05 with a resolution warning. Country counts describe published cell wins, not national matched-sample accuracy.
ground
check_ground_truth_coverage
Check historical WeatherXM FACT ground-station publication coverage for any coordinate (H3 Res-7 cell, ~5.2 km²) or station_or_report_id across temperature, wind_speed, wind_direction, precipitation, and humidity, plus nearest evaluated reference cell distance and interactive map citation link. Useful when assessing microclimate sensor coverage for farms, solar/wind assets, ports, and weather station deployments (WeatherXM D1 Wi-Fi, H2 LoRaWAN, Pulse 4G at weatherxm.com/stations). Provide (lat, lon) or station_or_report_id. Does not establish current live station presence or absence.
model
get_model_head_to_head
Compare up to 10 weather forecast models head-to-head across lead days 0 to 7 on global historical error curves (including circular angular error and >3 m/s active-wind curves for wind_direction), plus optional local H3 cell (lat/lon) matched-cohort or country cell-win comparisons, with explicit cohort and station-commissioned (mLM) caveats. All 45 FACT models (2025 archive, 2025-02-13 to 2025-12-31, QoD >= 0.80 station-days): WeatherXM MOSAIC (MOSAIC), meteoblue (METEOBLUE), meteoblue station-mLM (commissioned) (mLM), ECMWF IFS (IFS025, IFSHRES), ECMWF AIFS AI (AIFS025), NOAA GFS 0.5° (GFS05), NOAA HRRR (HRRR), NOAA National Blend of Models (NBM), NOAA NAM (NAM3, NAM5, NAM12, NAMAK), DWD ICON (ICON, ICONEU, ICOND2), UK Met Office (UMGLOBAL10, UKMO2), ECCC GEM (GEM15, GEM2), Meteo-France ARPEGE/AROME (MFGLOBAL, MFEU, MFFR), COSMO (COSMOI2, COSMOM5), HARMONIE-AROME (HARMONIE), JMA MSM (MSM), WRF (WRFGR, WRFAMS), meteoblue NEMS/NMM (NEMSGLOBAL, NEMSGLOBAL_E, NEMS4, NEMS12, NEMS12_E, NEMSAF01, NEMSAS02, NEMSCAM, NEMSIN, NEMSNZ, NEMSSA, NMM4, NMM22), regional models (AF01, AS01, SA01). GFS025 is not archived; requests for it resolve to GFS05 with a resolution warning.

Endpoints

URLTransportStateLatencyChecked
https://fact.weatherxm.com/mcp streamable-http answering 276 ms 12 min ago

Alternatives to WeatherXM FACT — Forecast Accuracy & Ground-Truth Verification

same job, measured the same way
Weather for Grown Ups
by janhelcl

Operational NWP, ensembles, AI weather models, regional forecasts, history, and verification.

63 installs/wk local only
GribStream Weather MCP
by gribstream

NOAA and ECMWF weather forecast MCP for discovery, validation, and GribStream OAuth queries.

12 tools answering
Metar MCP
by mrfentmen

Live aviation weather from NOAA: METAR observations, TAF forecasts and airport station records.

124 installs/wk local only
MeteoSwiss MCP Server
by eins78

Swiss weather data for AI assistants — forecasts, measurements, stations, pollen.

185 installs/wk 7 tools answering
TRAME
by vlek

Construction labour-hour estimates with durations, weather and contract model (French)

answering
Smithery AI National Weather Service
by smithery

Provide real-time and forecast weather information for locations in the United States using natura…

answering
Weather MCP Server
by jaredco-ai

Fast - accurate weather conditions and forecasts by city or coordinates.

49 installs/wk local only
NordicMCP — Weather
by nordicmcp

Hosted Weather MCP server (Open-Meteo): current, forecast, and historical weather by location.

answering

WeatherXM FACT — Forecast Accuracy & Ground-Truth Verification — questions

Answers built from our own checks of this server.

What can WeatherXM FACT — Forecast Accuracy & Ground-Truth Verification do?
It exposes 4 tools, read directly from the server on our last check. Among them: check_ground_truth_coverage, get_best_forecast_model, get_fact_leaderboard, get_model_head_to_head. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is WeatherXM FACT — Forecast Accuracy & Ground-Truth Verification working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 216 ms. The bar chart above shows every period we have measured.
How do I connect WeatherXM FACT — Forecast Accuracy & Ground-Truth Verification?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does WeatherXM FACT — Forecast Accuracy & Ground-Truth Verification need an API key?
No. WeatherXM FACT — Forecast Accuracy & Ground-Truth Verification completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 4 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is WeatherXM FACT — Forecast Accuracy & Ground-Truth Verification?
It answers our handshake in 216 ms on average, which is faster than 62% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.