io.github.cyanheads/open-meteo-mcp-server

Official11 toolsLive

by cyanheads · TypeScript

Global weather via Open-Meteo: forecast, historical, marine, air quality, geocoding, elevation.

@cyanheads/open-meteo-mcp-server

The io.github.cyanheads/open-meteo-mcp-server is an MCP server that provides global weather and related datasets via Open-Meteo, exposed as MCP tools. It supports fetching weather forecasts, ERA5 historical archive data, marine conditions, air quality, geocoding, and terrain elevation.

🛠️ Key Features

Global weather via Open-Meteo
Forecast retrieval
ERA5 archive (historical climate)
Marine conditions
Air quality
Geocoding places
Elevation (terrain)

🚀 Use Cases

Agent-driven weather lookup for locations
Historical climate or ERA5-based analysis queries
Marine and air-quality checks for relevant coordinates
Terrain elevation enrichment for location-based workflows

⚡ Developer Benefits

Implements MCP model context with 11 tools
Tool discovery enabled by MCP integration
Transport options include STDIO and Streamable HTTP

⚠️ Limitations

Scope is limited to Open-Meteo-provided domains: forecast, ERA5 archive, marine, air quality, geocoding, and elevation.

Topics

ai-agentsai-toolsclimatecyanheadsforecastmcpmcp-servermodel-context-protocolopen-meteotypescriptweather

Captured live from the server via tools/list.

openmeteo_search_locations

Resolve a place name to ranked coordinate matches with country, region, elevation, timezone, and population. Required prerequisite for name-based queries — all weather tools take latitude/longitude, not place names. Search by a bare place name (city, region, or landmark); never fold a qualifier into it — pass "Baoding", not "Baoding Hebei", and "Paris", not "Paris, France". To disambiguate places that share a name, set the country input (ISO 3166-1 alpha-2, e.g. "US") and/or read the admin1 and country fields on each ranked result — admin1 is a result field for choosing among matches, not a search input. Returns up to 10 matches ranked by population/relevance.

Parameters4

name	string	required	Place name to search — a bare city, region, or landmark ("Seattle", "Mount Rainier"). Do not fold in a region or country qualifier ("Baoding", not "Baoding Hebei"); use the country input to disambiguate. A one- or two-character native-script name ("서울", "大阪") needs the full administrative name ("서울특별시", "大阪市") or the romanized name ("Seoul", "Osaka") — see the language field. Weather tools require coordinates — use the lat/lon from this result.
country	string	optional	ISO 3166-1 alpha-2 country code (e.g. "US", "FR") to disambiguate places that share a name. Omit for a global search.
count	integer	optional	Max results to return (1–10). Default 5. Return more when disambiguating common names like "Springfield" or "Portland".
language	string	optional	Language for matching and returning place names (ISO 639-1, e.g., "en", "de", "zh"). The API matches name against the localized index for this language, so set it to match the script of name — e.g. language "zh" for "上海", "ru" for "Москва". This resolves a native-script name of three or more characters, which is matched by normalized prefix; a one- or two-character name must equal an index entry exactly, so setting language alone will not find "서울" or "大阪" — retry those with the full administrative name ("서울특별시", "大阪市") or the romanized name ("Seoul", "Osaka"). Default "en"; a query in a recognized non-Latin script (CJK, Hangul, Cyrillic, Arabic, Greek, Hebrew, Thai, Devanagari) that misses under "en" is retried once with the language inferred from its script.

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "minLength": 1,
      "maxLength": 100,
      "description": "Place name to search — a bare city, region, or landmark (\"Seattle\", \"Mount Rainier\"). Do not fold in a region or country qualifier (\"Baoding\", not \"Baoding Hebei\"); use the country input to disambiguate. A one- or two-character native-script name (\"서울\", \"大阪\") needs the full administrative name (\"서울특별시\", \"大阪市\") or the romanized name (\"Seoul\", \"Osaka\") — see the language field. Weather tools require coordinates — use the lat/lon from this result."
    },
    "country": {
      "description": "ISO 3166-1 alpha-2 country code (e.g. \"US\", \"FR\") to disambiguate places that share a name. Omit for a global search.",
      "type": "string",
      "pattern": "^[A-Za-z]{2}$"
    },
    "count": {
      "default": 5,
      "description": "Max results to return (1–10). Default 5. Return more when disambiguating common names like \"Springfield\" or \"Portland\".",
      "type": "integer",
      "minimum": 1,
      "maximum": 10
    },
    "language": {
      "default": "en",
      "description": "Language for matching and returning place names (ISO 639-1, e.g., \"en\", \"de\", \"zh\"). The API matches name against the localized index for this language, so set it to match the script of name — e.g. language \"zh\" for \"上海\", \"ru\" for \"Москва\". This resolves a native-script name of three or more characters, which is matched by normalized prefix; a one- or two-character name must equal an index entry exactly, so setting language alone will not find \"서울\" or \"大阪\" — retry those with the full administrative name (\"서울특별시\", \"大阪市\") or the romanized name (\"Seoul\", \"Osaka\"). Default \"en\"; a query in a recognized non-Latin script (CJK, Hangul, Cyrillic, Arabic, Greek, Hebrew, Thai, Devanagari) that misses under \"en\" is retried once with the language inferred from its script.",
      "type": "string"
    }
  },
  "required": [
    "name"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}

openmeteo_get_elevation

Terrain elevation from the Copernicus Digital Elevation Model (~90m resolution) for one or more coordinate pairs. Accepts up to 100 pairs per call. Useful for geographic context, elevation-adjusted weather interpretation, or route planning.

Parameters2

latitudes	array	required	Array of latitudes in decimal degrees (up to 100). Must be same length as longitudes.
longitudes	array	required	Array of longitudes in decimal degrees (up to 100). Must be same length as latitudes.

Raw schema

{
  "type": "object",
  "properties": {
    "latitudes": {
      "minItems": 1,
      "maxItems": 100,
      "type": "array",
      "items": {
        "type": "number",
        "minimum": -90,
        "maximum": 90
      },
      "description": "Array of latitudes in decimal degrees (up to 100). Must be same length as longitudes."
    },
    "longitudes": {
      "minItems": 1,
      "maxItems": 100,
      "type": "array",
      "items": {
        "type": "number",
        "minimum": -180,
        "maximum": 180
      },
      "description": "Array of longitudes in decimal degrees (up to 100). Must be same length as latitudes."
    }
  },
  "required": [
    "latitudes",
    "longitudes"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}

openmeteo_get_forecast

Weather forecast for coordinates: hourly and/or daily variables for up to 16 days ahead, with optional past_days (up to 92) for recent history. Use past_days instead of openmeteo_get_historical for dates within the last 1–5 days, since the archive’s ERA5 components lag by up to ~5 days. Returns per-timestamp records — each hourly entry contains a "time" field (ISO 8601) plus one key per requested variable; each daily entry contains a "time" field (YYYY-MM-DD) plus requested variables. Common hourly variables: temperature_2m, precipitation, wind_speed_10m, relative_humidity_2m, cloud_cover, uv_index, apparent_temperature, precipitation_probability, weather_code, surface_pressure, visibility, wind_direction_10m, wind_gusts_10m, dew_point_2m. Common daily variables: temperature_2m_max, temperature_2m_min, precipitation_sum, wind_speed_10m_max, sunrise, sunset, uv_index_max, precipitation_hours, weather_code. Set current_variables for conditions at this instant — Open-Meteo serves those from 15-minute model data, which is more precise than picking the nearest hourly row, and the response carries a current object plus a current_units map. A wide window — a large past_days plus many hourly variables — produces thousands of records; these spill to a DataCanvas when canvas is enabled, returning canvas_id and table_name with truncated: true — inspect the staged columns with openmeteo_dataframe_describe, then query the full set with openmeteo_dataframe_query. With canvas disabled they return a bounded preview instead. At least one of current_variables, hourly_variables, or daily_variables is required.

Parameters12

latitude	number	required	Latitude in decimal degrees (e.g., 47.6062 for Seattle). Use openmeteo_search_locations to resolve a place name to coordinates.
longitude	number	required	Longitude in decimal degrees (e.g., -122.3321 for Seattle).
current_variables	array	optional	Variables to return for the current instant (e.g., ["temperature_2m", "precipitation", "wind_speed_10m", "weather_code"]). Uses Open-Meteo's 15-minute current-conditions data, so it answers "what is it doing right now?" without requesting an hourly series and picking a row. Takes the hourly variable names; a daily-only name such as temperature_2m_max comes back null with the unit "undefined" and is reported in the notice. Satisfies the variable requirement on its own.
hourly_variables	array	optional	Hourly variables to fetch (e.g., ["temperature_2m", "precipitation", "wind_speed_10m", "relative_humidity_2m", "cloud_cover", "uv_index", "apparent_temperature"]). Hourly names only — a daily aggregate such as temperature_2m_max or precipitation_sum belongs in daily_variables and is rejected here. At least one of current_variables, hourly_variables, or daily_variables is required.
daily_variables	array	optional	Daily summary variables (e.g., ["temperature_2m_max", "temperature_2m_min", "precipitation_sum", "wind_speed_10m_max", "sunrise", "sunset", "uv_index_max"]). Daily names only — an hourly name such as cloud_cover or temperature_2m belongs in hourly_variables and is rejected here; for a daily summary of an hourly variable use its published aggregate (cloud_cover_max, cloud_cover_mean, cloud_cover_min). At least one of current_variables, hourly_variables, or daily_variables is required.
forecast_days	integer	optional	Number of forecast days (1–16). Default 7.
past_days	integer	optional	Include this many days of past data before today (0–92). Use for recent history — the archive’s ERA5 components lag by up to ~5 days. Default 0.
temperature_unit	string	optional	Temperature unit. Default "celsius".
wind_speed_unit	string	optional	Wind speed unit: "kmh" (km/h), "mph", "ms" (m/s), or "kn" (knots). Default "kmh".
precipitation_unit	string	optional	Precipitation unit: "mm" or "inch". Default "mm".
timezone	string	optional	IANA timezone (e.g., "America/Los_Angeles") or "auto" to use the location's local timezone. Default "auto". The timezone from openmeteo_search_locations is ideal to pass here.
canvas_id	string	optional	DataCanvas token for wide past_days or multi-variable queries. When a result is too large to return inline — driven by total payload size, so a wide multi-variable pull can spill at any row count — it spills to this canvas: pass the returned token to openmeteo_dataframe_describe to list the staged table and its columns, then to openmeteo_dataframe_query to run SQL against it. Omit to create a fresh canvas.

Raw schema

{
  "type": "object",
  "properties": {
    "latitude": {
      "type": "number",
      "minimum": -90,
      "maximum": 90,
      "description": "Latitude in decimal degrees (e.g., 47.6062 for Seattle). Use openmeteo_search_locations to resolve a place name to coordinates."
    },
    "longitude": {
      "type": "number",
      "minimum": -180,
      "maximum": 180,
      "description": "Longitude in decimal degrees (e.g., -122.3321 for Seattle)."
    },
    "current_variables": {
      "description": "Variables to return for the current instant (e.g., [\"temperature_2m\", \"precipitation\", \"wind_speed_10m\", \"weather_code\"]). Uses Open-Meteo's 15-minute current-conditions data, so it answers \"what is it doing right now?\" without requesting an hourly series and picking a row. Takes the hourly variable names; a daily-only name such as temperature_2m_max comes back null with the unit \"undefined\" and is reported in the notice. Satisfies the variable requirement on its own.",
      "maxItems": 50,
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "hourly_variables": {
      "description": "Hourly variables to fetch (e.g., [\"temperature_2m\", \"precipitation\", \"wind_speed_10m\", \"relative_humidity_2m\", \"cloud_cover\", \"uv_index\", \"apparent_temperature\"]). Hourly names only — a daily aggregate such as temperature_2m_max or precipitation_sum belongs in daily_variables and is rejected here. At least one of current_variables, hourly_variables, or daily_variables is required.",
      "maxItems": 50,
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "daily_variables": {
      "description": "Daily summary variables (e.g., [\"temperature_2m_max\", \"temperature_2m_min\", \"precipitation_sum\", \"wind_speed_10m_max\", \"sunrise\", \"sunset\", \"uv_index_max\"]). Daily names only — an hourly name such as cloud_cover or temperature_2m belongs in hourly_variables and is rejected here; for a daily summary of an hourly variable use its published aggregate (cloud_cover_max, cloud_cover_mean, cloud_cover_min). At least one of current_variables, hourly_variables, or daily_variables is required.",
      "maxItems": 50,
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "forecast_days": {
      "default": 7,
      "description": "Number of forecast days (1–16). Default 7.",
      "type": "integer",
      "minimum": 1,
      "maximum": 16
    },
    "past_days": {
      "default": 0,
      "description": "Include this many days of past data before today (0–92). Use for recent history — the archive’s ERA5 components lag by up to ~5 days. Default 0.",
      "type": "integer",
      "minimum": 0,
      "maximum": 92
    },
    "temperature_unit": {
      "default": "celsius",
      "description": "Temperature unit. Default \"celsius\".",
      "type": "string",
      "enum": [
        "celsius",
        "fahrenheit"
      ]
    },
    "wind_speed_unit": {
      "default": "kmh",
      "description": "Wind speed unit: \"kmh\" (km/h), \"mph\", \"ms\" (m/s), or \"kn\" (knots). Default \"kmh\".",
      "type": "string",
      "enum": [
        "kmh",
        "mph",
        "ms",
        "kn"
      ]
    },
    "precipitation_unit": {
      "default": "mm",
      "description": "Precipitation unit: \"mm\" or \"inch\". Default \"mm\".",
      "type": "string",
      "enum": [
        "mm",
        "inch"
      ]
    },
    "timezone": {
      "default": "auto",
      "description": "IANA timezone (e.g., \"America/Los_Angeles\") or \"auto\" to use the location's local timezone. Default \"auto\". The timezone from openmeteo_search_locations is ideal to pass here.",
      "type": "string"
    },
    "canvas_id": {
      "description": "DataCanvas token for wide past_days or multi-variable queries. When a result is too large to return inline — driven by total payload size, so a wide multi-variable pull can spill at any row count — it spills to this canvas: pass the returned token to openmeteo_dataframe_describe to list the staged table and its columns, then to openmeteo_dataframe_query to run SQL against it. Omit to create a fresh canvas.",
      "type": "string"
    }
  },
  "required": [
    "latitude",
    "longitude"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}

openmeteo_get_historical

Historical weather from the Open-Meteo reanalysis archive (1940–present). Requires start_date and end_date (ISO 8601 date, e.g., "2024-07-01"). With models omitted the archive answers from Best Match, which blends IFS HRES, ERA5, and ERA5-Land seamlessly — so the source varies by date and no single update lag describes the response. Set models to pin a consistent source for a multi-decade series: the ERA5 family updates daily with about a 5-day delay, while IFS HRES has none, so for the last few days either request models: ["ecmwf_ifs"] or use openmeteo_get_forecast with past_days. Available models: best_match (default, blends IFS HRES + ERA5 + ERA5-Land), ecmwf_ifs (global 9 km, updated every 6 hours, no delay), ecmwf_ifs_analysis_long_window (global 9 km, daily, 2 days delay), era5_seamless (ERA5 and ERA5-Land combined), era5 (global 0.25° (~25 km), daily, 5 days delay), era5_land (global 0.1° (~11 km), daily, 5 days delay), era5_ensemble (global 0.5° (~55 km), daily, 5 days delay), cerra (Europe only, 5 km, no real-time updates). Uses the same variable names as the forecast API for direct comparison. Large date ranges (multi-year hourly) produce thousands of records — these spill to a DataCanvas when canvas is enabled, returning canvas_id and table_name with truncated: true; inspect the staged columns with openmeteo_dataframe_describe, then query the full set with openmeteo_dataframe_query. With canvas disabled they return a bounded preview instead. At least one of hourly_variables or daily_variables is required.

Parameters12

latitude	number	required	Latitude in decimal degrees. Use openmeteo_search_locations to resolve a place name to coordinates.
longitude	number	required	Longitude in decimal degrees.
start_date	string	required	Start date (YYYY-MM-DD, e.g., "2024-07-01"). The archive covers from 1940-01-01; how close to today it reaches depends on the model — the ERA5 family runs about 5 days behind, IFS HRES is current.
end_date	string	required	End date (YYYY-MM-DD, inclusive). Must be on or after start_date. For the last few days, either request models: ["ecmwf_ifs"] or use openmeteo_get_forecast with past_days.
hourly_variables	array	optional	Hourly archive variables (e.g., ["temperature_2m", "precipitation", "wind_speed_10m", "relative_humidity_2m", "cloud_cover", "soil_moisture_0_to_7cm"]). Hourly names only — a daily aggregate such as temperature_2m_max or precipitation_sum belongs in daily_variables and is rejected here. At least one of hourly_variables or daily_variables required.
daily_variables	array	optional	Daily summary variables (e.g., ["temperature_2m_max", "temperature_2m_min", "precipitation_sum", "wind_speed_10m_max"]). Daily names only — an hourly name such as cloud_cover or temperature_2m belongs in hourly_variables and is rejected here; for a daily summary of an hourly variable use its published aggregate (cloud_cover_max, cloud_cover_mean, cloud_cover_min). At least one of hourly_variables or daily_variables required.
models	array	optional	Archive models to read from: best_match (default, blends IFS HRES + ERA5 + ERA5-Land), ecmwf_ifs (global 9 km, updated every 6 hours, no delay), ecmwf_ifs_analysis_long_window (global 9 km, daily, 2 days delay), era5_seamless (ERA5 and ERA5-Land combined), era5 (global 0.25° (~25 km), daily, 5 days delay), era5_land (global 0.1° (~11 km), daily, 5 days delay), era5_ensemble (global 0.5° (~55 km), daily, 5 days delay), cerra (Europe only, 5 km, no real-time updates). Omit to use Open-Meteo's Best Match default, which blends IFS HRES, ERA5, and ERA5-Land — pin a model instead when a consistent source matters across the range. With 2+ models each variable column is suffixed with the model name. cerra covers Europe only and is rejected as a coverage gap elsewhere. A name outside this list is sent upstream rather than rejected here.
temperature_unit	string	optional	Temperature unit. Default "celsius".
wind_speed_unit	string	optional	Wind speed unit. Default "kmh".
precipitation_unit	string	optional	Precipitation unit. Default "mm".
timezone	string	optional	IANA timezone or "auto". Default "auto".
canvas_id	string	optional	DataCanvas token for multi-year or multi-variable queries. When a result is too large to return inline — driven by total payload size, so a wide multi-variable pull can spill at any row count — it spills to this canvas: pass the returned token to openmeteo_dataframe_describe to list the staged table and its columns, then to openmeteo_dataframe_query to run SQL against it. Omit to create a fresh canvas.

Raw schema

{
  "type": "object",
  "properties": {
    "latitude": {
      "type": "number",
      "minimum": -90,
      "maximum": 90,
      "description": "Latitude in decimal degrees. Use openmeteo_search_locations to resolve a place name to coordinates."
    },
    "longitude": {
      "type": "number",
      "minimum": -180,
      "maximum": 180,
      "description": "Longitude in decimal degrees."
    },
    "start_date": {
      "type": "string",
      "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
      "description": "Start date (YYYY-MM-DD, e.g., \"2024-07-01\"). The archive covers from 1940-01-01; how close to today it reaches depends on the model — the ERA5 family runs about 5 days behind, IFS HRES is current."
    },
    "end_date": {
      "type": "string",
      "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
      "description": "End date (YYYY-MM-DD, inclusive). Must be on or after start_date. For the last few days, either request models: [\"ecmwf_ifs\"] or use openmeteo_get_forecast with past_days."
    },
    "hourly_variables": {
      "description": "Hourly archive variables (e.g., [\"temperature_2m\", \"precipitation\", \"wind_speed_10m\", \"relative_humidity_2m\", \"cloud_cover\", \"soil_moisture_0_to_7cm\"]). Hourly names only — a daily aggregate such as temperature_2m_max or precipitation_sum belongs in daily_variables and is rejected here. At least one of hourly_variables or daily_variables required.",
      "maxItems": 50,
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "daily_variables": {
      "description": "Daily summary variables (e.g., [\"temperature_2m_max\", \"temperature_2m_min\", \"precipitation_sum\", \"wind_speed_10m_max\"]). Daily names only — an hourly name such as cloud_cover or temperature_2m belongs in hourly_variables and is rejected here; for a daily summary of an hourly variable use its published aggregate (cloud_cover_max, cloud_cover_mean, cloud_cover_min). At least one of hourly_variables or daily_variables required.",
      "maxItems": 50,
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "models": {
      "description": "Archive models to read from: best_match (default, blends IFS HRES + ERA5 + ERA5-Land), ecmwf_ifs (global 9 km, updated every 6 hours, no delay), ecmwf_ifs_analysis_long_window (global 9 km, daily, 2 days delay), era5_seamless (ERA5 and ERA5-Land combined), era5 (global 0.25° (~25 km), daily, 5 days delay), era5_land (global 0.1° (~11 km), daily, 5 days delay), era5_ensemble (global 0.5° (~55 km), daily, 5 days delay), cerra (Europe only, 5 km, no real-time updates). Omit to use Open-Meteo's Best Match default, which blends IFS HRES, ERA5, and ERA5-Land — pin a model instead when a consistent source matters across the range. With 2+ models each variable column is suffixed with the model name. cerra covers Europe only and is rejected as a coverage gap elsewhere. A name outside this list is sent upstream rather than rejected here.",
      "maxItems": 8,
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "temperature_unit": {
      "default": "celsius",
      "description": "Temperature unit. Default \"celsius\".",
      "type": "string",
      "enum": [
        "celsius",
        "fahrenheit"
      ]
    },
    "wind_speed_unit": {
      "default": "kmh",
      "description": "Wind speed unit. Default \"kmh\".",
      "type": "string",
      "enum": [
        "kmh",
        "mph",
        "ms",
        "kn"
      ]
    },
    "precipitation_unit": {
      "default": "mm",
      "description": "Precipitation unit. Default \"mm\".",
      "type": "string",
      "enum": [
        "mm",
        "inch"
      ]
    },
    "timezone": {
      "default": "auto",
      "description": "IANA timezone or \"auto\". Default \"auto\".",
      "type": "string"
    },
    "canvas_id": {
      "description": "DataCanvas token for multi-year or multi-variable queries. When a result is too large to return inline — driven by total payload size, so a wide multi-variable pull can spill at any row count — it spills to this canvas: pass the returned token to openmeteo_dataframe_describe to list the staged table and its columns, then to openmeteo_dataframe_query to run SQL against it. Omit to create a fresh canvas.",
      "type": "string"
    }
  },
  "required": [
    "latitude",
    "longitude",
    "start_date",
    "end_date"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}

openmeteo_get_marine

Marine wave and ocean conditions for a coastal or ocean coordinate: wave height, wave period, wave direction, wind-wave height, swell height, sea-surface temperature. Forecast horizon up to 8 days, with optional past_days (up to 92) for recent history — or start_date and end_date together for an archive range, which returns real wave values back to at least 2022. One window per call: a date range is mutually exclusive with forecast_days and past_days, and needs both ends — a lone start_date or end_date is rejected. Returns per-timestamp records — each entry contains a "time" field plus one key per requested variable. Best for open-ocean and coastal exposed points — sheltered inland waters return near-zero wave values. Common hourly variables: wave_height, wave_direction, wave_period, wind_wave_height, wind_wave_direction, wind_wave_period, swell_wave_height, swell_wave_direction, swell_wave_period. Common daily: wave_height_max, wave_direction_dominant, wave_period_max. Note: ocean_current_velocity is null for non-open-ocean coordinates. A wide window — a large past_days or date range plus many variables — produces thousands of records; these spill to a DataCanvas when canvas is enabled, returning canvas_id and table_name with truncated: true — inspect the staged columns with openmeteo_dataframe_describe, then query the full set with openmeteo_dataframe_query. With canvas disabled they return a bounded preview instead.

Parameters10

latitude	number	required	Latitude of a coastal or ocean point. Use openmeteo_search_locations to resolve a place name. Inland points return near-zero wave values.
longitude	number	required	Longitude in decimal degrees.
hourly_variables	array	optional	Hourly marine variables (e.g., ["wave_height", "wave_direction", "wave_period", "wind_wave_height", "swell_wave_height"]). Hourly names only — a daily aggregate such as wave_height_max or wave_direction_dominant belongs in daily_variables and is rejected here. At least one of hourly_variables or daily_variables required.
daily_variables	array	optional	Daily marine summary variables (e.g., ["wave_height_max", "wave_direction_dominant", "wave_period_max"]). Daily names only — an hourly name such as wave_height belongs in hourly_variables and is rejected here; for a daily summary use its published aggregate (wave_height_max). At least one of hourly_variables or daily_variables required.
forecast_days	integer	optional	Forecast horizon in days (1–8). Omit for the upstream default of 7. Mutually exclusive with start_date/end_date — omit it entirely when pulling an archive range.
past_days	integer	optional	Include this many days of past data before today (0–92). Use for recent history instead of a start_date/end_date range. Default 0. Must stay 0 when start_date/end_date are used.
start_date	string	optional	Start date for the archive range (YYYY-MM-DD, e.g., "2024-07-01"). Real wave values go back to at least 2022. Requires end_date — the pair must be sent together, and neither combines with forecast_days or past_days.
end_date	string	optional	End date for the archive range (YYYY-MM-DD, inclusive). Must be on or after start_date. Requires start_date — the pair must be sent together, and neither combines with forecast_days or past_days.
timezone	string	optional	IANA timezone or "auto". Default "auto".
canvas_id	string	optional	DataCanvas token for wide past_days, archive-range, or multi-variable queries. When a result is too large to return inline — driven by total payload size, so a wide multi-variable pull can spill at any row count — it spills to this canvas: pass the returned token to openmeteo_dataframe_describe to list the staged table and its columns, then to openmeteo_dataframe_query to run SQL against it. Omit to create a fresh canvas.

Raw schema

{
  "type": "object",
  "properties": {
    "latitude": {
      "type": "number",
      "minimum": -90,
      "maximum": 90,
      "description": "Latitude of a coastal or ocean point. Use openmeteo_search_locations to resolve a place name. Inland points return near-zero wave values."
    },
    "longitude": {
      "type": "number",
      "minimum": -180,
      "maximum": 180,
      "description": "Longitude in decimal degrees."
    },
    "hourly_variables": {
      "description": "Hourly marine variables (e.g., [\"wave_height\", \"wave_direction\", \"wave_period\", \"wind_wave_height\", \"swell_wave_height\"]). Hourly names only — a daily aggregate such as wave_height_max or wave_direction_dominant belongs in daily_variables and is rejected here. At least one of hourly_variables or daily_variables required.",
      "maxItems": 50,
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "daily_variables": {
      "description": "Daily marine summary variables (e.g., [\"wave_height_max\", \"wave_direction_dominant\", \"wave_period_max\"]). Daily names only — an hourly name such as wave_height belongs in hourly_variables and is rejected here; for a daily summary use its published aggregate (wave_height_max). At least one of hourly_variables or daily_variables required.",
      "maxItems": 50,
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "forecast_days": {
      "description": "Forecast horizon in days (1–8). Omit for the upstream default of 7. Mutually exclusive with start_date/end_date — omit it entirely when pulling an archive range.",
      "type": "integer",
      "minimum": 1,
      "maximum": 8
    },
    "past_days": {
      "default": 0,
      "description": "Include this many days of past data before today (0–92). Use for recent history instead of a start_date/end_date range. Default 0. Must stay 0 when start_date/end_date are used.",
      "type": "integer",
      "minimum": 0,
      "maximum": 92
    },
    "start_date": {
      "description": "Start date for the archive range (YYYY-MM-DD, e.g., \"2024-07-01\"). Real wave values go back to at least 2022. Requires end_date — the pair must be sent together, and neither combines with forecast_days or past_days.",
      "type": "string",
      "pattern": "^\\d{4}-\\d{2}-\\d{2}$"
    },
    "end_date": {
      "description": "End date for the archive range (YYYY-MM-DD, inclusive). Must be on or after start_date. Requires start_date — the pair must be sent together, and neither combines with forecast_days or past_days.",
      "type": "string",
      "pattern": "^\\d{4}-\\d{2}-\\d{2}$"
    },
    "timezone": {
      "default": "auto",
      "description": "IANA timezone or \"auto\". Default \"auto\".",
      "type": "string"
    },
    "canvas_id": {
      "description": "DataCanvas token for wide past_days, archive-range, or multi-variable queries. When a result is too large to return inline — driven by total payload size, so a wide multi-variable pull can spill at any row count — it spills to this canvas: pass the returned token to openmeteo_dataframe_describe to list the staged table and its columns, then to openmeteo_dataframe_query to run SQL against it. Omit to create a fresh canvas.",
      "type": "string"
    }
  },
  "required": [
    "latitude",
    "longitude"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}

openmeteo_get_air_quality

Modeled CAMS (Copernicus Atmosphere Monitoring Service) air quality: PM2.5, PM10, nitrogen dioxide, sulphur dioxide, ozone, carbon monoxide, dust, pollen, and European/US AQI indices. This is modeled grid data, not measured station readings — for measured data, use openaq-mcp-server. Forecast horizon up to 7 days, with optional past_days (up to 92) for recent history — or start_date and end_date together for an archive range; the CAMS global archive begins in August 2022, and earlier dates return rows of nulls. One window per call: a date range is mutually exclusive with forecast_days and past_days, and needs both ends — a lone start_date or end_date is rejected. Common variables: pm2_5, pm10, carbon_monoxide, nitrogen_dioxide, sulphur_dioxide, ozone, dust, european_aqi, us_aqi, alder_pollen, birch_pollen, grass_pollen, mugwort_pollen, olive_pollen, ragweed_pollen. Set current_variables for pollutant and AQI values at this instant — returned as a current object plus a current_units map, and enough on its own without hourly_variables; the block’s interval field reports how often that value updates (3600 seconds on this endpoint). A wide window — a large past_days or date range plus many variables — produces thousands of records; these spill to a DataCanvas when canvas is enabled, returning canvas_id and table_name with truncated: true — inspect the staged columns with openmeteo_dataframe_describe, then query the full set with openmeteo_dataframe_query. With canvas disabled they return a bounded preview instead.

Parameters10

latitude	number	required	Latitude in decimal degrees. Use openmeteo_search_locations to resolve a place name.
longitude	number	required	Longitude in decimal degrees.
current_variables	array	optional	Air quality variables to return for the current instant (e.g., ["pm2_5", "pm10", "european_aqi", "us_aqi"]). Uses Open-Meteo's current-conditions data, so it answers "what is the AQI now?" without requesting an hourly series and picking a row; the returned interval reports the update cadence, 3600 seconds on this endpoint. Satisfies the variable requirement on its own.
hourly_variables	array	optional	Hourly air quality variables (e.g., ["pm2_5", "pm10", "ozone", "nitrogen_dioxide", "european_aqi", "us_aqi"]). At least one of current_variables or hourly_variables is required.
forecast_days	integer	optional	Forecast horizon in days (1–7). Omit for the upstream default of 5. Mutually exclusive with start_date/end_date — omit it entirely when pulling an archive range.
past_days	integer	optional	Include this many days of past data before today (0–92). Use for recent history instead of a start_date/end_date range. Default 0. Must stay 0 when start_date/end_date are used.
start_date	string	optional	Start date for the archive range (YYYY-MM-DD, e.g., "2024-07-01"). The CAMS global archive begins in August 2022; earlier dates return rows of nulls, and us_aqi starts a day later than the pollutant series (european_aqi starts with it). Requires end_date — the pair must be sent together, and neither combines with forecast_days or past_days.
end_date	string	optional	End date for the archive range (YYYY-MM-DD, inclusive). Must be on or after start_date. Requires start_date — the pair must be sent together, and neither combines with forecast_days or past_days.
timezone	string	optional	IANA timezone or "auto". Default "auto".
canvas_id	string	optional	DataCanvas token for wide past_days, archive-range, or multi-variable queries. When a result is too large to return inline — driven by total payload size, so a wide multi-variable pull can spill at any row count — it spills to this canvas: pass the returned token to openmeteo_dataframe_describe to list the staged table and its columns, then to openmeteo_dataframe_query to run SQL against it. Omit to create a fresh canvas.

Raw schema

{
  "type": "object",
  "properties": {
    "latitude": {
      "type": "number",
      "minimum": -90,
      "maximum": 90,
      "description": "Latitude in decimal degrees. Use openmeteo_search_locations to resolve a place name."
    },
    "longitude": {
      "type": "number",
      "minimum": -180,
      "maximum": 180,
      "description": "Longitude in decimal degrees."
    },
    "current_variables": {
      "description": "Air quality variables to return for the current instant (e.g., [\"pm2_5\", \"pm10\", \"european_aqi\", \"us_aqi\"]). Uses Open-Meteo's current-conditions data, so it answers \"what is the AQI now?\" without requesting an hourly series and picking a row; the returned interval reports the update cadence, 3600 seconds on this endpoint. Satisfies the variable requirement on its own.",
      "maxItems": 50,
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "hourly_variables": {
      "description": "Hourly air quality variables (e.g., [\"pm2_5\", \"pm10\", \"ozone\", \"nitrogen_dioxide\", \"european_aqi\", \"us_aqi\"]). At least one of current_variables or hourly_variables is required.",
      "maxItems": 50,
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "forecast_days": {
      "description": "Forecast horizon in days (1–7). Omit for the upstream default of 5. Mutually exclusive with start_date/end_date — omit it entirely when pulling an archive range.",
      "type": "integer",
      "minimum": 1,
      "maximum": 7
    },
    "past_days": {
      "default": 0,
      "description": "Include this many days of past data before today (0–92). Use for recent history instead of a start_date/end_date range. Default 0. Must stay 0 when start_date/end_date are used.",
      "type": "integer",
      "minimum": 0,
      "maximum": 92
    },
    "start_date": {
      "description": "Start date for the archive range (YYYY-MM-DD, e.g., \"2024-07-01\"). The CAMS global archive begins in August 2022; earlier dates return rows of nulls, and us_aqi starts a day later than the pollutant series (european_aqi starts with it). Requires end_date — the pair must be sent together, and neither combines with forecast_days or past_days.",
      "type": "string",
      "pattern": "^\\d{4}-\\d{2}-\\d{2}$"
    },
    "end_date": {
      "description": "End date for the archive range (YYYY-MM-DD, inclusive). Must be on or after start_date. Requires start_date — the pair must be sent together, and neither combines with forecast_days or past_days.",
      "type": "string",
      "pattern": "^\\d{4}-\\d{2}-\\d{2}$"
    },
    "timezone": {
      "default": "auto",
      "description": "IANA timezone or \"auto\". Default \"auto\".",
      "type": "string"
    },
    "canvas_id": {
      "description": "DataCanvas token for wide past_days, archive-range, or multi-variable queries. When a result is too large to return inline — driven by total payload size, so a wide multi-variable pull can spill at any row count — it spills to this canvas: pass the returned token to openmeteo_dataframe_describe to list the staged table and its columns, then to openmeteo_dataframe_query to run SQL against it. Omit to create a fresh canvas.",
      "type": "string"
    }
  },
  "required": [
    "latitude",
    "longitude"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}

openmeteo_get_ensemble

Probabilistic ensemble weather forecast — up to 64 ensemble members, up to 16 days ahead with optional past_days (0–92). Each member's values appear as separate columns named with a member suffix (e.g. temperature_2m_member01, temperature_2m_member02). Use the spread across members to compute exceedance probabilities, quantify forecast uncertainty, and build decision thresholds. Available models: ecmwf_ifs025_ensemble (51 members, global 0.25°), ecmwf_aifs025_ensemble (51, global 0.25°), ecmwf_ifs_europe_ensemble (51, Europe 9 km), ecmwf_aifs_europe_ensemble (51, Europe 31 km), google_weathernext2_ensemble (64, global 0.25°), ncep_gefs_seamless (31, global blend), ncep_gefs025 (31, global 0.25°), ncep_gefs05 (31, global 50 km, 35 days), ncep_aigefs025 (31, global 0.25°), icon_seamless_eps (20–40, global/Europe blend), icon_global_eps (40, global 26 km), icon_eu_eps (40, Europe 13 km), icon_d2_eps (20, Central Europe 2 km), gem_global_ensemble (21, global 0.25°), bom_access_global_ensemble (18, global 40 km), ukmo_global_ensemble_20km (18, global 20 km), ukmo_uk_ensemble_2km (3, UK 2 km), meteoswiss_icon_ch1_ensemble (11, Central Europe 1 km), meteoswiss_icon_ch2_ensemble (21, Central Europe 2 km). Omit models to use the API default blend. A regional model returns no data outside the area it covers; that comes back as an input error naming the coverage gap, not a transient failure, so pick a global model or move the coordinate inside the region rather than retrying. A model name this list does not carry is still sent upstream, so a newly added one keeps working. Large multi-member, multi-day pulls produce thousands of records and spill to a DataCanvas when canvas is enabled, returning canvas_id and table_name with truncated: true — inspect the staged columns with openmeteo_dataframe_describe, then query the full set with openmeteo_dataframe_query. With canvas disabled they return a bounded preview instead. At least one of hourly_variables or daily_variables is required.

Parameters12

latitude	number	required	Latitude in decimal degrees. Use openmeteo_search_locations to resolve a place name to coordinates.
longitude	number	required	Longitude in decimal degrees.
hourly_variables	array	optional	Hourly variables to fetch across all ensemble members (e.g., ["temperature_2m", "precipitation", "wind_speed_10m"]). Each variable appears as temperature_2m_member01, temperature_2m_member02, … in the output. Hourly names only — a daily-only aggregate such as precipitation_sum or wind_speed_10m_max belongs in daily_variables and is rejected here; temperature_2m_max and temperature_2m_min are an exception, published here as 3-hourly aggregations as well as daily. At least one of hourly_variables or daily_variables required.
daily_variables	array	optional	Daily variables to fetch across all ensemble members (e.g., ["temperature_2m_max", "temperature_2m_min", "precipitation_sum"]). Each variable appears as temperature_2m_max_member01, … Daily names only — an hourly name such as precipitation or temperature_2m belongs in hourly_variables and is rejected here; for a daily summary use its published aggregate (precipitation_sum, temperature_2m_max). At least one of hourly_variables or daily_variables required.
models	string	optional	Ensemble model to use, one name: ecmwf_ifs025_ensemble (51 members, global 0.25°), ecmwf_aifs025_ensemble (51, global 0.25°), ecmwf_ifs_europe_ensemble (51, Europe 9 km), ecmwf_aifs_europe_ensemble (51, Europe 31 km), google_weathernext2_ensemble (64, global 0.25°), ncep_gefs_seamless (31, global blend), ncep_gefs025 (31, global 0.25°), ncep_gefs05 (31, global 50 km, 35 days), ncep_aigefs025 (31, global 0.25°), icon_seamless_eps (20–40, global/Europe blend), icon_global_eps (40, global 26 km), icon_eu_eps (40, Europe 13 km), icon_d2_eps (20, Central Europe 2 km), gem_global_ensemble (21, global 0.25°), bom_access_global_ensemble (18, global 40 km), ukmo_global_ensemble_20km (18, global 20 km), ukmo_uk_ensemble_2km (3, UK 2 km), meteoswiss_icon_ch1_ensemble (11, Central Europe 1 km), meteoswiss_icon_ch2_ensemble (21, Central Europe 2 km). Member counts include the control run. Omit to use the API default blend. A name outside this list is sent upstream rather than rejected here, so a model Open-Meteo adds later still works.
forecast_days	integer	optional	Forecast horizon in days (1–16). Default 7.
past_days	integer	optional	Include this many days of past ensemble data before today (0–92). Default 0.
temperature_unit	string	optional	Temperature unit. Default "celsius".
wind_speed_unit	string	optional	Wind speed unit. Default "kmh".
precipitation_unit	string	optional	Precipitation unit. Default "mm".
timezone	string	optional	IANA timezone (e.g., "America/Los_Angeles") or "auto" to use the location's local timezone. Default "auto".
canvas_id	string	optional	DataCanvas token for large multi-member queries. When a result is too large to return inline — driven by total payload size, so a wide member fan-out can spill at any row count — it spills to this canvas: pass the returned token to openmeteo_dataframe_describe to list the staged table and its per-member columns, then to openmeteo_dataframe_query to run SQL against it. Omit to create a fresh canvas.

Raw schema

{
  "type": "object",
  "properties": {
    "latitude": {
      "type": "number",
      "minimum": -90,
      "maximum": 90,
      "description": "Latitude in decimal degrees. Use openmeteo_search_locations to resolve a place name to coordinates."
    },
    "longitude": {
      "type": "number",
      "minimum": -180,
      "maximum": 180,
      "description": "Longitude in decimal degrees."
    },
    "hourly_variables": {
      "description": "Hourly variables to fetch across all ensemble members (e.g., [\"temperature_2m\", \"precipitation\", \"wind_speed_10m\"]). Each variable appears as temperature_2m_member01, temperature_2m_member02, … in the output. Hourly names only — a daily-only aggregate such as precipitation_sum or wind_speed_10m_max belongs in daily_variables and is rejected here; temperature_2m_max and temperature_2m_min are an exception, published here as 3-hourly aggregations as well as daily. At least one of hourly_variables or daily_variables required.",
      "maxItems": 50,
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "daily_variables": {
      "description": "Daily variables to fetch across all ensemble members (e.g., [\"temperature_2m_max\", \"temperature_2m_min\", \"precipitation_sum\"]). Each variable appears as temperature_2m_max_member01, … Daily names only — an hourly name such as precipitation or temperature_2m belongs in hourly_variables and is rejected here; for a daily summary use its published aggregate (precipitation_sum, temperature_2m_max). At least one of hourly_variables or daily_variables required.",
      "maxItems": 50,
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "models": {
      "description": "Ensemble model to use, one name: ecmwf_ifs025_ensemble (51 members, global 0.25°), ecmwf_aifs025_ensemble (51, global 0.25°), ecmwf_ifs_europe_ensemble (51, Europe 9 km), ecmwf_aifs_europe_ensemble (51, Europe 31 km), google_weathernext2_ensemble (64, global 0.25°), ncep_gefs_seamless (31, global blend), ncep_gefs025 (31, global 0.25°), ncep_gefs05 (31, global 50 km, 35 days), ncep_aigefs025 (31, global 0.25°), icon_seamless_eps (20–40, global/Europe blend), icon_global_eps (40, global 26 km), icon_eu_eps (40, Europe 13 km), icon_d2_eps (20, Central Europe 2 km), gem_global_ensemble (21, global 0.25°), bom_access_global_ensemble (18, global 40 km), ukmo_global_ensemble_20km (18, global 20 km), ukmo_uk_ensemble_2km (3, UK 2 km), meteoswiss_icon_ch1_ensemble (11, Central Europe 1 km), meteoswiss_icon_ch2_ensemble (21, Central Europe 2 km). Member counts include the control run. Omit to use the API default blend. A name outside this list is sent upstream rather than rejected here, so a model Open-Meteo adds later still works.",
      "type": "string"
    },
    "forecast_days": {
      "default": 7,
      "description": "Forecast horizon in days (1–16). Default 7.",
      "type": "integer",
      "minimum": 1,
      "maximum": 16
    },
    "past_days": {
      "default": 0,
      "description": "Include this many days of past ensemble data before today (0–92). Default 0.",
      "type": "integer",
      "minimum": 0,
      "maximum": 92
    },
    "temperature_unit": {
      "default": "celsius",
      "description": "Temperature unit. Default \"celsius\".",
      "type": "string",
      "enum": [
        "celsius",
        "fahrenheit"
      ]
    },
    "wind_speed_unit": {
      "default": "kmh",
      "description": "Wind speed unit. Default \"kmh\".",
      "type": "string",
      "enum": [
        "kmh",
        "mph",
        "ms",
        "kn"
      ]
    },
    "precipitation_unit": {
      "default": "mm",
      "description": "Precipitation unit. Default \"mm\".",
      "type": "string",
      "enum": [
        "mm",
        "inch"
      ]
    },
    "timezone": {
      "default": "auto",
      "description": "IANA timezone (e.g., \"America/Los_Angeles\") or \"auto\" to use the location's local timezone. Default \"auto\".",
      "type": "string"
    },
    "canvas_id": {
      "description": "DataCanvas token for large multi-member queries. When a result is too large to return inline — driven by total payload size, so a wide member fan-out can spill at any row count — it spills to this canvas: pass the returned token to openmeteo_dataframe_describe to list the staged table and its per-member columns, then to openmeteo_dataframe_query to run SQL against it. Omit to create a fresh canvas.",
      "type": "string"
    }
  },
  "required": [
    "latitude",
    "longitude"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}

openmeteo_get_flood

GloFAS (Global Flood Awareness System) river discharge forecast and historical reanalysis. Returns daily ensemble river discharge (m³/s) for the largest modeled river within 5 km of the given coordinates — no river ID needed. That river is not always the closest one: at 5 km resolution a point near a confluence or a pair of parallel channels can resolve to an unintended reach. When the returned discharge looks unrepresentative for the intended river, Open-Meteo suggests varying the coordinate by about 0.1° and comparing the values. Forecast horizon up to 210 days ahead; reanalysis history back to 1984-01-01. One mode per call: forecast_days for the future outlook, or start_date and end_date together for reanalysis history. The two modes are mutually exclusive, and a date range needs both ends — a lone start_date or end_date is rejected. Available daily variables: "river_discharge" (ensemble mean), "river_discharge_mean", "river_discharge_min", "river_discharge_max", "river_discharge_median", "river_discharge_p25" (25th percentile), "river_discharge_p75" (75th percentile). Returns null for coordinates far from any river or in areas without GloFAS coverage. A wide reanalysis range produces thousands of daily records and spills to a DataCanvas when canvas is enabled, returning canvas_id and table_name with truncated: true — inspect the staged columns with openmeteo_dataframe_describe, then query the full set with openmeteo_dataframe_query. With canvas disabled it returns a bounded preview instead.

Parameters8

latitude	number	required	Latitude in decimal degrees. Discharge is returned for the largest modeled river within 5 km of this point — no river ID required, and not necessarily the closest river. Vary the coordinate by about 0.1° and compare when the result looks unrepresentative. Use openmeteo_search_locations to resolve a place name.
longitude	number	required	Longitude in decimal degrees. With latitude it selects the largest modeled river within 5 km, which is not necessarily the closest one.
daily_variables	array	optional	Daily discharge variables to fetch (e.g., ["river_discharge", "river_discharge_p25", "river_discharge_p75", "river_discharge_min", "river_discharge_max"]). Required.
forecast_days	integer	optional	Number of forecast days ahead (1–210). Mutually exclusive with start_date/end_date — omit it entirely when pulling a historical range.
start_date	string	optional	Start date for historical reanalysis (YYYY-MM-DD, e.g., "2023-01-01"). GloFAS reanalysis covers from 1984-01-01. Requires end_date — the pair must be sent together, and neither combines with forecast_days.
end_date	string	optional	End date for historical reanalysis (YYYY-MM-DD, inclusive). Must be on or after start_date. Requires start_date — the pair must be sent together, and neither combines with forecast_days.
timezone	string	optional	IANA timezone or "auto". Default "auto".
canvas_id	string	optional	DataCanvas token for wide reanalysis queries. When a result is too large to return inline — driven by total payload size, so a multi-variable pull can spill at any row count — it spills to this canvas: pass the returned token to openmeteo_dataframe_describe to list the staged table and its columns, then to openmeteo_dataframe_query to run SQL against it. Omit to create a fresh canvas.

Raw schema

{
  "type": "object",
  "properties": {
    "latitude": {
      "type": "number",
      "minimum": -90,
      "maximum": 90,
      "description": "Latitude in decimal degrees. Discharge is returned for the largest modeled river within 5 km of this point — no river ID required, and not necessarily the closest river. Vary the coordinate by about 0.1° and compare when the result looks unrepresentative. Use openmeteo_search_locations to resolve a place name."
    },
    "longitude": {
      "type": "number",
      "minimum": -180,
      "maximum": 180,
      "description": "Longitude in decimal degrees. With latitude it selects the largest modeled river within 5 km, which is not necessarily the closest one."
    },
    "daily_variables": {
      "description": "Daily discharge variables to fetch (e.g., [\"river_discharge\", \"river_discharge_p25\", \"river_discharge_p75\", \"river_discharge_min\", \"river_discharge_max\"]). Required.",
      "maxItems": 20,
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "forecast_days": {
      "description": "Number of forecast days ahead (1–210). Mutually exclusive with start_date/end_date — omit it entirely when pulling a historical range.",
      "type": "integer",
      "minimum": 1,
      "maximum": 210
    },
    "start_date": {
      "description": "Start date for historical reanalysis (YYYY-MM-DD, e.g., \"2023-01-01\"). GloFAS reanalysis covers from 1984-01-01. Requires end_date — the pair must be sent together, and neither combines with forecast_days.",
      "type": "string",
      "pattern": "^\\d{4}-\\d{2}-\\d{2}$"
    },
    "end_date": {
      "description": "End date for historical reanalysis (YYYY-MM-DD, inclusive). Must be on or after start_date. Requires start_date — the pair must be sent together, and neither combines with forecast_days.",
      "type": "string",
      "pattern": "^\\d{4}-\\d{2}-\\d{2}$"
    },
    "timezone": {
      "default": "auto",
      "description": "IANA timezone or \"auto\". Default \"auto\".",
      "type": "string"
    },
    "canvas_id": {
      "description": "DataCanvas token for wide reanalysis queries. When a result is too large to return inline — driven by total payload size, so a multi-variable pull can spill at any row count — it spills to this canvas: pass the returned token to openmeteo_dataframe_describe to list the staged table and its columns, then to openmeteo_dataframe_query to run SQL against it. Omit to create a fresh canvas.",
      "type": "string"
    }
  },
  "required": [
    "latitude",
    "longitude"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}

openmeteo_get_climate

Long-range climate projections from bias-corrected daily CMIP6 models, covering 1950-01-01 to 2050-12-31 at any coordinate. Answers "what will conditions look like through 2050?" — the future-projection counterpart to openmeteo_get_historical (the observed archive, what happened). Daily resolution only. Available models: CMCC_CM2_VHR4, FGOALS_f3_H, HiRAM_SIT_HR, MRI_AGCM3_2_S, EC_Earth3P_HR, MPI_ESM1_2_XR, NICAM16_8S. A model name outside that list is sent upstream rather than rejected here, so a model Open-Meteo adds later still works; if upstream rejects the request, the error names the offending model on its own rather than the whole requested list. With 2+ models each variable appears once per model with the model name as suffix (e.g. temperature_2m_max_CMCC_CM2_VHR4); a single or omitted model returns plain variable names. Not all models carry all variables — missing combinations return null. Multi-decade daily pulls across several models produce thousands of records and spill to a DataCanvas when canvas is enabled, returning canvas_id and table_name with truncated: true — inspect the staged columns with openmeteo_dataframe_describe, then query the full set with openmeteo_dataframe_query. With canvas disabled they return a bounded preview instead.

Parameters11

latitude	number	required	Latitude in decimal degrees. Use openmeteo_search_locations to resolve a place name to coordinates.
longitude	number	required	Longitude in decimal degrees.
start_date	string	required	Start date (YYYY-MM-DD, e.g., "2049-01-01"). CMIP6 projections cover 1950-01-01 to 2050-12-31.
end_date	string	required	End date (YYYY-MM-DD, inclusive, max 2050-12-31). Must be on or after start_date.
daily_variables	array	optional	Daily climate variables to fetch (e.g., ["temperature_2m_max", "temperature_2m_min", "precipitation_sum", "wind_speed_10m_mean", "shortwave_radiation_sum"]). Required — the Climate API is daily-only.
models	array	optional	CMIP6 models to include: CMCC_CM2_VHR4, FGOALS_f3_H, HiRAM_SIT_HR, MRI_AGCM3_2_S, EC_Earth3P_HR, MPI_ESM1_2_XR, NICAM16_8S. With 2+ models each variable column is suffixed with the model name (e.g. temperature_2m_max_MRI_AGCM3_2_S). Omit to use the API default (a single model, unsuffixed columns). A name outside this list is sent upstream rather than rejected here.
temperature_unit	string	optional	Temperature unit. Default "celsius".
wind_speed_unit	string	optional	Wind speed unit. Default "kmh".
precipitation_unit	string	optional	Precipitation unit. Default "mm".
timezone	string	optional	IANA timezone or "auto". Default "auto".
canvas_id	string	optional	DataCanvas token for multi-decade or multi-model queries. When a result is too large to return inline — driven by total payload size, so a wide multi-model pull can spill at any row count — it spills to this canvas: pass the returned token to openmeteo_dataframe_describe to list the staged table and its per-model columns, then to openmeteo_dataframe_query to run SQL against it. Omit to create a fresh canvas.

Raw schema

{
  "type": "object",
  "properties": {
    "latitude": {
      "type": "number",
      "minimum": -90,
      "maximum": 90,
      "description": "Latitude in decimal degrees. Use openmeteo_search_locations to resolve a place name to coordinates."
    },
    "longitude": {
      "type": "number",
      "minimum": -180,
      "maximum": 180,
      "description": "Longitude in decimal degrees."
    },
    "start_date": {
      "type": "string",
      "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
      "description": "Start date (YYYY-MM-DD, e.g., \"2049-01-01\"). CMIP6 projections cover 1950-01-01 to 2050-12-31."
    },
    "end_date": {
      "type": "string",
      "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
      "description": "End date (YYYY-MM-DD, inclusive, max 2050-12-31). Must be on or after start_date."
    },
    "daily_variables": {
      "description": "Daily climate variables to fetch (e.g., [\"temperature_2m_max\", \"temperature_2m_min\", \"precipitation_sum\", \"wind_speed_10m_mean\", \"shortwave_radiation_sum\"]). Required — the Climate API is daily-only.",
      "maxItems": 50,
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "models": {
      "description": "CMIP6 models to include: CMCC_CM2_VHR4, FGOALS_f3_H, HiRAM_SIT_HR, MRI_AGCM3_2_S, EC_Earth3P_HR, MPI_ESM1_2_XR, NICAM16_8S. With 2+ models each variable column is suffixed with the model name (e.g. temperature_2m_max_MRI_AGCM3_2_S). Omit to use the API default (a single model, unsuffixed columns). A name outside this list is sent upstream rather than rejected here.",
      "maxItems": 7,
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "temperature_unit": {
      "default": "celsius",
      "description": "Temperature unit. Default \"celsius\".",
      "type": "string",
      "enum": [
        "celsius",
        "fahrenheit"
      ]
    },
    "wind_speed_unit": {
      "default": "kmh",
      "description": "Wind speed unit. Default \"kmh\".",
      "type": "string",
      "enum": [
        "kmh",
        "mph",
        "ms",
        "kn"
      ]
    },
    "precipitation_unit": {
      "default": "mm",
      "description": "Precipitation unit. Default \"mm\".",
      "type": "string",
      "enum": [
        "mm",
        "inch"
      ]
    },
    "timezone": {
      "default": "auto",
      "description": "IANA timezone or \"auto\". Default \"auto\".",
      "type": "string"
    },
    "canvas_id": {
      "description": "DataCanvas token for multi-decade or multi-model queries. When a result is too large to return inline — driven by total payload size, so a wide multi-model pull can spill at any row count — it spills to this canvas: pass the returned token to openmeteo_dataframe_describe to list the staged table and its per-model columns, then to openmeteo_dataframe_query to run SQL against it. Omit to create a fresh canvas.",
      "type": "string"
    }
  },
  "required": [
    "latitude",
    "longitude",
    "start_date",
    "end_date"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}

openmeteo_dataframe_query

Run a read-only SQL SELECT against tables staged on a DataCanvas by openmeteo_get_forecast, openmeteo_get_historical, openmeteo_get_marine, openmeteo_get_air_quality, openmeteo_get_ensemble, openmeteo_get_flood, or openmeteo_get_climate. Pass the canvas_id returned when any of those tools spills (truncated: true), and reference the exact table_name those tools return alongside it. Call openmeteo_dataframe_describe to list staged tables and their columns when you need to discover names.

Parameters2

canvas_id	string	required	Canvas ID returned by openmeteo_get_forecast, openmeteo_get_historical, openmeteo_get_marine, openmeteo_get_air_quality, openmeteo_get_ensemble, openmeteo_get_flood, or openmeteo_get_climate when truncated: true.
sql	string	required	Read-only SELECT statement. Reference table names from openmeteo_dataframe_describe. Example: SELECT AVG(temperature_2m) AS avg_temp, strftime(time, '%Y-%m') AS month FROM spilled_abc123 GROUP BY month ORDER BY month

Raw schema

{
  "type": "object",
  "properties": {
    "canvas_id": {
      "type": "string",
      "description": "Canvas ID returned by openmeteo_get_forecast, openmeteo_get_historical, openmeteo_get_marine, openmeteo_get_air_quality, openmeteo_get_ensemble, openmeteo_get_flood, or openmeteo_get_climate when truncated: true."
    },
    "sql": {
      "type": "string",
      "description": "Read-only SELECT statement. Reference table names from openmeteo_dataframe_describe. Example: SELECT AVG(temperature_2m) AS avg_temp, strftime(time, '%Y-%m') AS month FROM spilled_abc123 GROUP BY month ORDER BY month"
    }
  },
  "required": [
    "canvas_id",
    "sql"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}

openmeteo_dataframe_describe

List the tables and their columns on a DataCanvas staged by openmeteo_get_forecast, openmeteo_get_historical, openmeteo_get_marine, openmeteo_get_air_quality, openmeteo_get_ensemble, openmeteo_get_flood, or openmeteo_get_climate. Call this first to discover table names before querying with openmeteo_dataframe_query.

Parameters1

canvas_id

string

required

Canvas ID returned by openmeteo_get_forecast, openmeteo_get_historical, openmeteo_get_marine, openmeteo_get_air_quality, openmeteo_get_ensemble, openmeteo_get_flood, or openmeteo_get_climate when truncated: true.

Raw schema

{
  "type": "object",
  "properties": {
    "canvas_id": {
      "type": "string",
      "description": "Canvas ID returned by openmeteo_get_forecast, openmeteo_get_historical, openmeteo_get_marine, openmeteo_get_air_quality, openmeteo_get_ensemble, openmeteo_get_flood, or openmeteo_get_climate when truncated: true."
    }
  },
  "required": [
    "canvas_id"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}

README.md24 KBView on GitHub

@cyanheads/open-meteo-mcp-server

Geocode places, fetch global weather forecasts, historical climate, marine conditions, air quality, and terrain elevation via MCP. STDIO or Streamable HTTP.

11 Tools

Version MCP SDK TypeScript

Public Hosted Server: https://open-meteo.caseyjhand.com/mcp

Overview

Global weather from Open-Meteo: forecasts, historical archive, marine conditions, air quality, probabilistic ensembles, river discharge, and CMIP6 climate projections. Geocode place names, pull hourly and daily variables, and run SQL over large results staged to DataCanvas. Runs as a stdio process, a local Streamable HTTP server, or the public hosted endpoint above.

Tools

Tool	Description
`openmeteo_search_locations`	Resolve a place name to ranked coordinate matches with country, region, elevation, timezone, and population
`openmeteo_get_forecast`	Weather forecast for coordinates: current conditions and/or hourly and daily variables for up to 16 days, with optional recent past data; wide windows spill to DataCanvas
`openmeteo_get_historical`	Historical weather from the Open-Meteo reanalysis archive (1940–present); Best Match by default, or pin a `models` selection; large ranges spill to DataCanvas
`openmeteo_get_marine`	Marine wave and ocean conditions for coastal or ocean coordinates: wave height, period, direction, swell, and sea-surface temperature; up to 8 forecast days, `past_days`, or a `start_date`/`end_date` archive range; large windows spill to DataCanvas
`openmeteo_get_air_quality`	Modeled CAMS air quality: PM2.5, PM10, NO2, O3, CO, dust, pollen, and European/US AQI indices; current conditions, up to 7 forecast days, `past_days`, or a `start_date`/`end_date` archive range; large windows spill to DataCanvas
`openmeteo_get_elevation`	Terrain elevation from Copernicus DEM (~90m resolution) for up to 100 coordinate pairs per call
`openmeteo_get_ensemble`	Probabilistic ensemble forecast: per-member hourly/daily time series (up to 51 members, 16 days) for exceedance and uncertainty analysis
`openmeteo_get_flood`	GloFAS river discharge forecast (up to 210 days) or reanalysis (1984–present); coordinate-based, resolving to the largest river within 5 km; large ranges spill to DataCanvas
`openmeteo_get_climate`	Bias-corrected daily CMIP6 climate projections (1950–2050) across up to 7 models; large ranges spill to DataCanvas
`openmeteo_dataframe_describe`	List tables and columns on a DataCanvas staged by `openmeteo_get_forecast`, `openmeteo_get_historical`, `openmeteo_get_marine`, `openmeteo_get_air_quality`, `openmeteo_get_ensemble`, `openmeteo_get_flood`, or `openmeteo_get_climate`
`openmeteo_dataframe_query`	Run a read-only SQL SELECT against tables staged on a DataCanvas

Capability reference

`openmeteo_search_locations` _tool

Returns name, country, admin1/admin2, latitude, longitude, elevation, IANA timezone, population, and GeoNames feature code
Search by a bare place name — a city, region, or landmark ("Baoding", not "Baoding Hebei"; "Paris", not "Paris, France"); a compound "City Region" or "City, Country" string matches nothing
Disambiguate same-named places (e.g., "Springfield") with the optional country filter (ISO 3166-1 alpha-2) or by raising count (default 5, up to 10) and reading admin1/country on each result
Pass the timezone from a result directly to weather tools as the timezone parameter
Fails with a no_results error (not an empty array) when nothing matches
When the top match has null or sub-100,000 population, the response carries an advisory notice naming that place, its country, and its feature code — historic and colonial exonyms ("Bangalore", "Calcutta") can resolve to an unrelated small feature rather than the modern city

`openmeteo_get_forecast` _tool

Up to 16 forecast days (forecast_days, default 7) plus optional past_days (0–92) for recent history — prefer past_days over openmeteo_get_historical for the last ~5 days, where the archive's ERA5 components lag
At least one of current_variables, hourly_variables, or daily_variables is required; current_variables alone satisfies it and returns a current object plus current_units from Open-Meteo's 15-minute current-conditions data
Hourly and daily are separate variable sets — a variable documented under the other cadence is rejected before the request, naming the field it belongs in and same-cadence alternatives
Configurable temperature, wind-speed, and precipitation units; reshapes the columnar API response into per-timestamp records with parallel hourly_units/daily_units maps
A wide window (large past_days plus many hourly variables) spills to DataCanvas when CANVAS_PROVIDER_TYPE=duckdb — output carries canvas_id and truncated: true; an over-wide request Open-Meteo refuses outright fails as request_too_large, naming the levers to narrow it

`openmeteo_get_historical` _tool

Requires start_date and end_date (YYYY-MM-DD); archive covers 1940-01-01 to present
Omitting models reads Best Match (blends IFS HRES, ERA5, and ERA5-Land — source varies by date); pass models to pin one: era5/era5_land/era5_ensemble update daily with about a 5-day delay, ecmwf_ifs has none, cerra covers Europe only (elsewhere it fails as a coverage-gap error). Not an allowlist — an unlisted name still goes upstream
With 2+ models each variable column is suffixed with the model name
Same variable vocabulary as openmeteo_get_forecast for direct past/forecast comparison; at least one of hourly_variables or daily_variables is required, and the two are separate sets — a wrong-cadence name is rejected before the request
Large date ranges (multi-year hourly) spill to DataCanvas when CANVAS_PROVIDER_TYPE=duckdb — output carries canvas_id and truncated: true; query via openmeteo_dataframe_describe then openmeteo_dataframe_query

`openmeteo_get_marine` _tool

Up to 8 forecast days (forecast_days, upstream default 7) with optional past_days (0–92), or an archive range via start_date/end_date (real wave values go back to at least 2022)
One window per call — a date range is mutually exclusive with forecast_days/past_days, and needs both ends (a lone start_date or end_date is rejected)
At least one of hourly_variables or daily_variables is required; the two are separate sets — a wrong-cadence name is rejected before the request
Inland or sheltered-water points return near-zero wave values (physically correct, not an error); ocean_current_velocity is null for non-open-ocean coordinates
Wide windows spill to DataCanvas when CANVAS_PROVIDER_TYPE=duckdb — output carries canvas_id and truncated: true; query with openmeteo_dataframe_query

`openmeteo_get_air_quality` _tool

Up to 7 forecast days (forecast_days, upstream default 5) with optional past_days (0–92), or an archive range via start_date/end_date — the CAMS global archive begins August 2022; earlier dates return nulls, and us_aqi starts a day later than the pollutant series
One window per call — a date range is mutually exclusive with forecast_days/past_days, and needs both ends
At least one of current_variables or hourly_variables is required; current_variables alone answers "right now" (a current object plus current_units, interval 3600s on this endpoint)
Grid-modeled CAMS data, coarser than ground stations — cross-reference openaq-mcp-server for measured readings; output carries data_source: "CAMS" to distinguish the two
Wide windows spill to DataCanvas when CANVAS_PROVIDER_TYPE=duckdb — output carries canvas_id and truncated: true; query with openmeteo_dataframe_query

`openmeteo_get_elevation` _tool

Accepts parallel latitudes[]/longitudes[] arrays of equal length, up to 100 pairs per call
Returns results in input order: { latitude, longitude, elevation_m } from the Copernicus DEM (~90m resolution)
Useful for geographic context, elevation-adjusted weather interpretation, or route planning

`openmeteo_get_ensemble` _tool

Up to 16 forecast days (forecast_days, default 7) with optional past_days (0–92); at least one of hourly_variables or daily_variables is required, and the two are separate sets (though this endpoint's own catalog publishes temperature_2m_max/_min under both)
Each requested variable returns as per-member columns (temperature_2m_member01, temperature_2m_member02, …) across up to 64 members — use the spread for exceedance probabilities and uncertainty ranges
models selects one global or regional ensemble (member counts vary, e.g. ecmwf_ifs025_ensemble 51, gem_global_ensemble 21); omit for the API default blend. Not an allowlist — an unlisted name still goes upstream
A regional model queried outside its coverage area fails as a non-retryable input error naming the gap — switch to a global model rather than retrying
Large multi-member, multi-day pulls spill to DataCanvas when CANVAS_PROVIDER_TYPE=duckdb — output carries canvas_id and truncated: true; query with openmeteo_dataframe_query

`openmeteo_get_flood` _tool

Coordinate-based — no river ID needed; discharge comes from the largest modeled river within 5 km of the point, which is not always the closest one. Vary the coordinate by about 0.1° and compare when a result looks unrepresentative
Forecast horizon up to 210 days (forecast_days); reanalysis history from 1984-01-01 to present via start_date/end_date
One mode per call — forecast_days is mutually exclusive with a start_date/end_date range, and the range needs both ends
Daily variables: river_discharge (ensemble mean), river_discharge_mean/_min/_max/_median, river_discharge_p25/_p75 — all in m³/s; returns null for coordinates outside GloFAS coverage
Wide reanalysis ranges spill to DataCanvas when CANVAS_PROVIDER_TYPE=duckdb — output carries canvas_id and truncated: true; query with openmeteo_dataframe_query

`openmeteo_get_climate` _tool

Coverage 1950-01-01 to 2050-12-31, daily resolution only — the future-projection counterpart to openmeteo_get_historical
Up to 7 bias-corrected CMIP6 models (e.g. CMCC_CM2_VHR4, MRI_AGCM3_2_S); not an allowlist — an unlisted name still goes upstream, and a multi-model rejection names only the offending model
With 2+ models each variable appears once per model, suffixed with the model name; a single or omitted model returns plain variable names
Not all models carry all variables — missing combinations return null rather than an error
Multi-decade daily pulls across several models spill to DataCanvas when CANVAS_PROVIDER_TYPE=duckdb — output carries canvas_id and truncated: true; query with openmeteo_dataframe_query

`openmeteo_dataframe_describe` _tool

Lists tables and columns on a DataCanvas staged by any of the seven spillover tools (openmeteo_get_forecast, _historical, _marine, _air_quality, _ensemble, _flood, _climate) — call this first, since table and column names are generated per request
Fails with canvas_not_enabled when CANVAS_PROVIDER_TYPE is not duckdb, or canvas_not_found when canvas_id is unknown or past its 24-hour sliding TTL
Output includes each table's row count, column types, and nullability, plus the canvas's expires_at

`openmeteo_dataframe_query` _tool

Runs a read-only SQL SELECT against tables staged by the seven spillover tools — pass the canvas_id and reference the exact table_name they return, or discover both via openmeteo_dataframe_describe
Fails with canvas_not_enabled when CANVAS_PROVIDER_TYPE is not duckdb, canvas_not_found when canvas_id is unknown or past its 24-hour sliding TTL, or missing_table when the SQL references a table not staged on the canvas
System catalogs (information_schema, sqlite_master, pg_catalog, duckdb_*() functions) are blocked so callers cannot enumerate other staged canvases — fails as system_catalog_access
Result rows are capped at 100 inline; row_count reports the full total — page further results with LIMIT/OFFSET in the SQL

Features

Built on @cyanheads/mcp-ts-core: stdio and Streamable HTTP transports, pluggable auth (none / jwt / oauth), swappable storage (in-memory, filesystem, Supabase, Cloudflare KV/R2/D1), structured logging with optional OpenTelemetry tracing.

Open-Meteo-specific:

No API key required for non-commercial use — zero-config out of the box; commercial use requires Open-Meteo's paid API tier
Self-contained geocoding — openmeteo_search_locations resolves place names so agents don't need a separate geocoder
Historical archive from 1940 to present on the same variable schema as the forecast API, with a models selector for pinning the reanalysis source
Automatic columnar-to-record reshape — Open-Meteo's parallel time/variable arrays become per-timestamp records with a *_units map
DataCanvas spillover for all seven forecast/archive tools — an over-budget result stages a DuckDB dataframe for SQL querying; with CANVAS_PROVIDER_TYPE=none (the default) those tools return a bounded preview with truncated: true instead

Agent-friendly output:

Location-first workflow — openmeteo_search_locations returns the IANA timezone alongside coordinates, ready to pass straight to any weather tool's timezone parameter
Discriminated rejections — an over-wide request fails as request_too_large naming the levers to shrink it, distinct from a rate-limit rejection, which is not retried
Cadence-aware validation — a variable documented under the wrong cadence (hourly vs. daily) is rejected before the upstream call, naming the field it belongs in and same-cadence alternatives
Notice on silent data changes — an unserved variable name or a snapped-to-grid coordinate surfaces in the response notice rather than passing as an unremarked data gap

Getting started

Public Hosted Instance

A public instance is available at https://open-meteo.caseyjhand.com/mcp — no installation required. Point any MCP client at it via Streamable HTTP:

json

{
  "mcpServers": {
    "open-meteo-mcp-server": {
      "type": "streamable-http",
      "url": "https://open-meteo.caseyjhand.com/mcp"
    }
  }
}

Self-Hosted / Local

Add the following to your MCP client configuration file.

json

{
  "mcpServers": {
    "open-meteo-mcp-server": {
      "type": "stdio",
      "command": "bunx",
      "args": ["@cyanheads/open-meteo-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info"
      }
    }
  }
}

Or with npx (no Bun required):

json

{
  "mcpServers": {
    "open-meteo-mcp-server": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@cyanheads/open-meteo-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info"
      }
    }
  }
}

Or with Docker:

json

{
  "mcpServers": {
    "open-meteo-mcp-server": {
      "type": "stdio",
      "command": "docker",
      "args": ["run", "-i", "--rm", "-e", "MCP_TRANSPORT_TYPE=stdio", "ghcr.io/cyanheads/open-meteo-mcp-server:latest"]
    }
  }
}

For Streamable HTTP, set the transport and start the server:

MCP_TRANSPORT_TYPE=http MCP_HTTP_PORT=3010 bun run start:http
# Server listens at http://localhost:3010/mcp

Prerequisites

Bun v1.4.0 or higher (or Node.js v24+).
No API key required. Non-commercial use is free and keyless.
Commercial use requires Open-Meteo's paid API tier.

Installation

Clone the repository:

git clone https://github.com/cyanheads/open-meteo-mcp-server.git

Navigate into the directory:

cd open-meteo-mcp-server

Install dependencies:

bun install

Configuration

All configuration is validated at startup via Zod schemas. No API key is required for non-commercial use — all variables are optional.

Variable	Description	Default
`MCP_TRANSPORT_TYPE`	Transport: `stdio` or `http`	`stdio`
`MCP_HTTP_PORT`	HTTP server port	`3010`
`MCP_HTTP_HOST`	HTTP server host	`127.0.0.1`
`MCP_HTTP_ENDPOINT_PATH`	HTTP endpoint path	`/mcp`
`MCP_HTTP_MAX_BODY_BYTES`	Maximum HTTP request body bytes; `0` disables the limit.	`1048576`
`MCP_PUBLIC_URL`	Public origin for TLS-terminating reverse-proxy deployments	—
`MCP_SESSION_MODE`	HTTP session mode: `auto`, `stateful`, or `stateless`. The server declares `stateless` in code, so it applies when this is unset; set a value to override it. `auto` resolves to `stateful`.	`stateless`
`MCP_HTTP_RESUMABILITY`	Replay missed SSE events for stateful HTTP sessions. No effect on stateless mode or protocol revision 2026-07-28.	`true`
`MCP_HTTP_RESUMABILITY_MAX_EVENTS`	Events retained per stateful session for replay; oldest evicted first.	`512`
`MCP_HTTP_RESUMABILITY_TTL_MS`	How long retained events remain replayable (ms).	`300000`
`MCP_AUTH_MODE`	Auth mode: `none`, `jwt`, or `oauth`	`none`
`MCP_LOG_LEVEL`	Log level (`debug`, `info`, `notice`, `warning`, `error`)	`info`
`MCP_LOG_RATE_LIMIT_THRESHOLD`	Maximum repeated emissions per level and message in each log window; `0` disables suppression.	`10`
`MCP_LOG_RATE_LIMIT_WINDOW_MS`	Repeated-log suppression window (ms).	`60000`
`MCP_GC_PRESSURE_INTERVAL_MS`	Opt-in forced-GC interval (ms, Bun only). Set to `60000` if heap growth is observed under sustained HTTP traffic.	`0`
`LOGS_DIR`	Directory for log files (Node.js only)	`<project-root>/logs`
`STORAGE_PROVIDER_TYPE`	Storage backend: `in-memory`, `filesystem`, `supabase`, `cloudflare-kv/r2/d1`	`in-memory`
`CANVAS_PROVIDER_TYPE`	Canvas engine for `openmeteo_get_forecast` / `openmeteo_get_historical` / `openmeteo_get_marine` / `openmeteo_get_air_quality` / `openmeteo_get_ensemble` / `openmeteo_get_flood` / `openmeteo_get_climate` spillover: `duckdb` or `none`. At `none` those tools still bound an over-budget response to a preview and set `truncated: true` — there is just no canvas holding the rows they omit	`none`
`OPEN_METEO_API_BASE_URL`	Override for the main forecast + elevation API	`https://api.open-meteo.com`
`OPEN_METEO_ARCHIVE_BASE_URL`	Override for the historical archive API	`https://archive-api.open-meteo.com`
`OPEN_METEO_MARINE_BASE_URL`	Override for the marine forecast API	`https://marine-api.open-meteo.com`
`OPEN_METEO_AIR_QUALITY_BASE_URL`	Override for the CAMS air quality API	`https://air-quality-api.open-meteo.com`
`OPEN_METEO_GEOCODING_BASE_URL`	Override for the geocoding API	`https://geocoding-api.open-meteo.com`
`OPEN_METEO_ENSEMBLE_BASE_URL`	Override for the ensemble forecast API	`https://ensemble-api.open-meteo.com`
`OPEN_METEO_FLOOD_BASE_URL`	Override for the GloFAS flood API	`https://flood-api.open-meteo.com`
`OPEN_METEO_CLIMATE_BASE_URL`	Override for the CMIP6 climate projections API	`https://climate-api.open-meteo.com`
`OTEL_ENABLED`	Enable OpenTelemetry tracing and metrics	`false`

See .env.example for the full list of optional overrides.

Running the server

Local development

Build and run the production version:

# One-time build
bun run rebuild

# Run the built server
bun run start:http
# or
bun run start:stdio

Run checks and tests:

bun run devcheck  # Lint, format, typecheck, security
bun run test      # Vitest test suite

Docker

docker build -t open-meteo-mcp-server .
docker run --rm -p 3010:3010 open-meteo-mcp-server

The Dockerfile defaults to HTTP transport, stateless session mode, and logs to /var/log/open-meteo-mcp-server. OpenTelemetry peer dependencies are installed by default — build with --build-arg OTEL_ENABLED=false to omit them.

Project structure

Directory	Purpose
`src/index.ts`	`createApp()` entry point — registers tools, initializes the Open-Meteo service
`src/config`	Server-specific environment variable parsing and validation with Zod
`src/mcp-server/tools/definitions`	Tool definitions (`*.tool.ts`) — one file per tool; includes `dataframe-describe.tool.ts` and `dataframe-query.tool.ts`
`src/services/open-meteo`	Open-Meteo HTTP client wrapping all nine endpoints with retry, error classification, and columnar reshape
`src/services/canvas-accessor.ts`	DataCanvas accessor for `openmeteo_get_forecast` / `openmeteo_get_historical` / `openmeteo_get_marine` / `openmeteo_get_air_quality` / `openmeteo_get_ensemble` / `openmeteo_get_flood` / `openmeteo_get_climate` spillover
`tests/`	Unit and integration tests mirroring `src/`

Development guide

See CLAUDE.md for development guidelines and architectural rules. The short version:

Handlers throw, framework catches — no try/catch in tool logic
Use ctx.log for request-scoped logging, ctx.state for tenant-scoped storage
Register new tools in the tools[] array in src/index.ts
Wrap external API calls: validate raw → normalize to domain type → return output schema; never fabricate missing fields

Attribution

Weather data by Open-Meteo.com, licensed CC BY 4.0.

Contributing

Issues are welcome. Run checks and tests before submitting:

bun run devcheck
bun run test

License

Apache-2.0 — see LICENSE for details.

Install

Tools (11)

openmeteo_search_locationsopenmeteo_get_elevationopenmeteo_get_forecastopenmeteo_get_historicalopenmeteo_get_marineopenmeteo_get_air_qualityopenmeteo_get_ensembleopenmeteo_get_flood

Configuration

Environment variables

MCP_LOG_LEVELdefault info

Sets the minimum log level for output (e.g., 'debug', 'info', 'warn').

CANVAS_PROVIDER_TYPEdefault none

Canvas engine for openmeteo_get_forecast / openmeteo_get_historical / openmeteo_get_marine / openmeteo_get_air_quality / openmeteo_get_ensemble / openmeteo_get_flood / openmeteo_get_climate spillover. Set to 'duckdb' to enable DataCanvas and the dataframe_query / dataframe_describe tools. Default 'none' — those tools still bound an over-budget response to a preview with truncated: true, but nothing stages the rows they omit.

MCP_HTTP_HOSTdefault 127.0.0.1

The hostname for the HTTP server.

MCP_HTTP_PORTdefault 3010

The port to run the HTTP server on.

MCP_HTTP_ENDPOINT_PATHdefault /mcp

The endpoint path for the MCP server.

MCP_AUTH_MODEdefault none

Authentication mode to use: 'none', 'jwt', or 'oauth'.

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "open-meteo-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@cyanheads/open-meteo-mcp-server@0.3.11",
        "run",
        "start:stdio"
      ],
      "env": {
        "MCP_LOG_LEVEL": "info",
        "CANVAS_PROVIDER_TYPE": "none"
      }
    }
  }
}

@cyanheads/open-meteo-mcp-server

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

Topics

openmeteo_search_locations

openmeteo_get_elevation

openmeteo_get_forecast

openmeteo_get_historical

openmeteo_get_marine

openmeteo_get_air_quality

openmeteo_get_ensemble

openmeteo_get_flood

openmeteo_get_climate

openmeteo_dataframe_query

openmeteo_dataframe_describe

@cyanheads/open-meteo-mcp-server

Overview

Tools

Capability reference

openmeteo_search_locations tool

openmeteo_get_forecast tool

openmeteo_get_historical tool

openmeteo_get_marine tool

openmeteo_get_air_quality tool

openmeteo_get_elevation tool

openmeteo_get_ensemble tool

openmeteo_get_flood tool

openmeteo_get_climate tool

openmeteo_dataframe_describe tool

openmeteo_dataframe_query tool

Features

Getting started

Public Hosted Instance

Self-Hosted / Local

Prerequisites

Installation

Configuration

Running the server

Local development

Docker

Project structure

Development guide

Attribution

Contributing

License

Install

Configuration

Related servers

`openmeteo_search_locations` _tool

`openmeteo_get_forecast` _tool

`openmeteo_get_historical` _tool

`openmeteo_get_marine` _tool

`openmeteo_get_air_quality` _tool

`openmeteo_get_elevation` _tool

`openmeteo_get_ensemble` _tool

`openmeteo_get_flood` _tool

`openmeteo_get_climate` _tool

`openmeteo_dataframe_describe` _tool

`openmeteo_dataframe_query` _tool