WeatherXM FACT MCP

An official MCP server for WeatherXM FACT that allows AI agents to benchmark 45 NWP and AI weather forecast models against 10,000+ ground stations. It provides tools to find the best forecast model for specific coordinates, check ground-truth coverage, access global or country-level accuracy leaderboards, and perform head-to-head model comparisons using verified historical error metrics.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Vendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-07Operated by WeatherXM

MCP endpoint (Streamable HTTP)

https://fact.weatherxm.com/mcp

Vendor documentation

What its tools do

4 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

4 of 4 have a description · 4 of 4 declare behavior hints · 0 of 4 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

Passed Endpoint answered the live check · Nov 7, 2026, 8:00 AM UTC
Passed Official MCP Registry namespace is tied to fact.weatherxm.com · Nov 7, 2026, 6:07 AM UTC
Passed Endpoint is on the registry namespace domain · Nov 7, 2026, 6:07 AM UTC
Availability 1 of 1 checks passed in 30 days

What you can do with it

Find the most accurate weather forecast model for a specific location and variable
Check ground-truth station coverage for any coordinate
Access global or country-level weather forecast accuracy leaderboards
Compare up to 10 weather models head-to-head across lead days

Source and maintenance

Vendor evidenceRegistry 2.1.0

mcp-registry: com.weatherxm.fact/mcp@2.1.0 Project website

Protocol and capabilities

Server: weatherxm-fact-mcp 2.1.0
MCP protocol negotiated in check: 2025-11-25
Tools: 4 advertised
Resources: Not advertised
Resource templates: Not advertised
Prompts: Not advertised

Server-advertised capabilities

{
  "tools": {
    "listChanged": false
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

Historical FACT archive only. Preserve provenance, missing-result and cohort caveats. Do not interpret publication gaps as no stations or historical MAE as a guarantee.

Tools

4 advertised

get_best_forecast_model

Advertised by the server during the last successful anonymous check.

Advertised read-only

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, precipitation, humidity), and forecast horizon (Days 0-7). All 45 FACT models: WeatherXM MOSAIC (MOSAIC), meteoblue (METEOBLUE), meteoblue station-mLM (mLM), ECMWF IFS (IFS025, IFSHRES), ECMWF AIFS AI (AIFS025), NOAA GFS (GFS05, GFS025), 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), and regional models (AF01, AS01, SA01). 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.

get_best_forecast_model input schema

{
  "type": "object",
  "properties": {
    "lat": {
      "type": "number",
      "maximum": 90,
      "minimum": -90
    },
    "lon": {
      "type": "number",
      "maximum": 180,
      "minimum": -180
    },
    "lead_day": {
      "enum": [
        "all",
        "0",
        "1",
        "2",
        "3",
        "4",
        "5",
        "6",
        "7"
      ],
      "type": "string"
    },
    "variable": {
      "enum": [
        "temperature",
        "wind_speed",
        "precipitation",
        "humidity"
      ],
      "type": "string",
      "default": "temperature"
    },
    "exclude_commissioned": {
      "type": "boolean",
      "default": false
    },
    "station_or_report_id": {
      "type": "string",
      "maxLength": 80,
      "description": "Optional WeatherXM station UUID or custom site evaluation report ID (e.g. STUDY-...)"
    }
  },
  "additionalProperties": false
}

get_best_forecast_model annotations

{
  "title": "Get Best Weather Forecast Model",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

check_ground_truth_coverage

Advertised by the server during the last successful anonymous check.

Advertised read-only

Check historical WeatherXM FACT ground-station publication coverage for any coordinate (H3 Res-7 cell, ~5.2 km²) or station_or_report_id, 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.

check_ground_truth_coverage input schema

{
  "type": "object",
  "properties": {
    "lat": {
      "type": "number",
      "maximum": 90,
      "minimum": -90
    },
    "lon": {
      "type": "number",
      "maximum": 180,
      "minimum": -180
    },
    "lead_day": {
      "enum": [
        "all",
        "0",
        "1",
        "2",
        "3",
        "4",
        "5",
        "6",
        "7"
      ],
      "type": "string"
    },
    "variable": {
      "enum": [
        "temperature",
        "wind_speed",
        "precipitation",
        "humidity"
      ],
      "type": "string",
      "default": "temperature"
    },
    "exclude_commissioned": {
      "type": "boolean",
      "default": false
    },
    "station_or_report_id": {
      "type": "string",
      "maxLength": 80,
      "description": "Optional WeatherXM station UUID or custom site evaluation report ID (e.g. STUDY-...)"
    }
  },
  "additionalProperties": false
}

check_ground_truth_coverage annotations

{
  "title": "Check Ground-Truth Station Coverage",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

get_fact_leaderboard

Advertised by the server during the last successful anonymous check.

Advertised read-only

Read the global weather forecast accuracy leaderboard (MAE, RMSE, 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: WeatherXM MOSAIC (MOSAIC), meteoblue (METEOBLUE), meteoblue station-mLM (mLM), ECMWF IFS (IFS025, IFSHRES), ECMWF AIFS AI (AIFS025), NOAA GFS (GFS05, GFS025), 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), and regional models (AF01, AS01, SA01). Country counts describe published cell wins, not national matched-sample accuracy.

get_fact_leaderboard input schema

{
  "type": "object",
  "properties": {
    "country": {
      "type": "string",
      "maxLength": 80
    },
    "lead_day": {
      "enum": [
        "all",
        "0",
        "1",
        "2",
        "3",
        "4",
        "5",
        "6",
        "7"
      ],
      "type": "string"
    },
    "variable": {
      "enum": [
        "temperature",
        "wind_speed",
        "precipitation",
        "humidity"
      ],
      "type": "string",
      "default": "temperature"
    },
    "exclude_commissioned": {
      "type": "boolean",
      "default": false
    }
  },
  "additionalProperties": false
}

get_fact_leaderboard annotations

{
  "title": "Get Forecast Accuracy Leaderboard",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

get_model_head_to_head

Advertised by the server during the last successful anonymous check.

Advertised read-only

Compare up to 10 weather forecast models head-to-head across lead days 0 to 7 on global historical error curves, with explicit cohort and station-commissioned (mLM) caveats. All 45 FACT models: WeatherXM MOSAIC (MOSAIC), meteoblue (METEOBLUE), meteoblue station-mLM (mLM), ECMWF IFS (IFS025, IFSHRES), ECMWF AIFS AI (AIFS025), NOAA GFS (GFS05, GFS025), 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), and regional models (AF01, AS01, SA01).

get_model_head_to_head input schema

{
  "type": "object",
  "properties": {
    "models": {
      "type": "array",
      "items": {
        "type": "string",
        "maxLength": 40
      },
      "maxItems": 10,
      "minItems": 1
    },
    "variable": {
      "enum": [
        "temperature",
        "wind_speed",
        "precipitation",
        "humidity"
      ],
      "type": "string",
      "default": "temperature"
    }
  },
  "additionalProperties": false
}

get_model_head_to_head annotations

{
  "title": "Compare Forecast Models Head-to-Head",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (1 of 1 answered).

2026-11-07: 1 of 1 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks: 1 of 1 (100%)
Average latency: 424 ms
95th percentile latency: 424 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

Nov 7, 2026, 8:00 AM UTC · probe · passed · 424 ms · metadata changed · 4 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.

Claude Code configuration

claude mcp add --transport http weatherxm-fact-mcp https://fact.weatherxm.com/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).

Codex configuration

codex mcp add weatherxm-fact-mcp --url https://fact.weatherxm.com/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable weatherxm-fact-mcp in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "weatherxm-fact-mcp": {
      "url": "https://fact.weatherxm.com/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).

Cline configuration

{
  "mcpServers": {
    "weatherxm-fact-mcp": {
      "type": "streamableHttp",
      "url": "https://fact.weatherxm.com/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start weatherxm-fact-mcp and inspect its tools.

VS Code configuration

{
  "servers": {
    "weatherxm-fact-mcp": {
      "type": "http",
      "url": "https://fact.weatherxm.com/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.

Gemini CLI configuration

gemini mcp add --transport http weatherxm-fact-mcp https://fact.weatherxm.com/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.

Claude Desktop configuration

https://fact.weatherxm.com/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

{
  "mcpServers": {
    "weatherxm-fact-mcp": {
      "serverUrl": "https://fact.weatherxm.com/mcp"
    }
  }
}

Let your agent find its tools

Find servers like WeatherXM FACT MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows

See all 7,033

Do you run WeatherXM FACT MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing

WeatherXM FACT MCP

Endpoint and access

What its tools do

Read-only (4)

Checks and signals

What you can do with it

Source and maintenance

Protocol and capabilities

Server-provided instructions

Tools

Prompts

Resources

90-day uptime

30-day availability

Maintenance history

Connect from your client

Claude Code

Codex

Cursor

Cline

VS Code

Gemini CLI

Claude Desktop

Windsurf

Let your agent find its tools

Other data and analytics servers

Do you run WeatherXM FACT MCP?