dynamical.org Weather & Climate Catalog is an MCP server published by io.github.dynamical-org, hosted at mcp.dynamical.org. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 4 tools, including get_access_pattern, get_dataset_info, list_recent_runs, search_catalog.
Search dynamical.org's open STAC catalog of weather & climate datasets (GFS, ECMWF, HRRR).
Nothing else in the archive shares these values.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Get the storage URI and working code for opening a dynamical.org dataset's data. dynamical.org publishes a Python package, `dynamical-catalog`, that reads the STAC catalog itself to resolve and open a dataset -- it's the recommended access pattern because it can't go stale even if the underlying storage format or location changes. This tool also returns the dataset's low-level storage details (from the STAC asset, fetched live) and a lower-level xarray/fsspec snippet for callers who need direct access instead of the wrapper package. Args: collection_id: A STAC collection id, e.g. "noaa-gfs-forecast". Use search_catalog to discover ids. Returns: A dict with the recommended `dynamical_catalog.open(...)` snippet, a `worked_example` pulled from the collection's own STAC metadata when one is published, the raw asset URI/type/storage options, and a generated low-level open snippet (icechunk/zarr/geoparquet, chosen from the asset's declared type). Raises ValueError (listing valid ids) if collection_id is unknown.
| Parameter | Type | Description |
|---|---|---|
| collection_id * | string |
None yet. Changes appear after a server's second daily check.
Inferred from the host name and headers: what a server runs on, not who runs it.
{
"name": "get_access_pattern",
"title": "Get data access snippet",
"description": "Get the storage URI and working code for opening a dynamical.org\ndataset's data.\n\ndynamical.org publishes a Python package, `dynamical-catalog`, that\nreads the STAC catalog itself to resolve and open a dataset -- it's the\nrecommended access pattern because it can't go stale even if the\nunderlying storage format or location changes. This tool also returns\nthe dataset's low-level storage details (from the STAC asset, fetched\nlive) and a lower-level xarray/fsspec snippet for callers who need\ndirect access instead of the wrapper package.\n\nArgs:\n collection_id: A STAC collection id, e.g. \"noaa-gfs-forecast\". Use\n search_catalog to discover ids.\n\nReturns:\n A dict with the recommended `dynamical_catalog.open(...)` snippet,\n a `worked_example` pulled from the collection's own STAC metadata\n when one is published, the raw asset URI/type/storage options, and\n a generated low-level open snippet (icechunk/zarr/geoparquet,\n chosen from the asset's declared type). Raises ValueError (listing\n valid ids) if collection_id is unknown.\n",
"inputSchema": {
"type": "object",
"title": "get_access_patternArguments",
"required": [
"collection_id"
],
"properties": {
"collection_id": {
"type": "string",
"title": "Collection Id"
}
}
},
"outputSchema": {
"type": "object",
"title": "get_access_patternDictOutput",
"additionalProperties": true
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true
}
}Get documentation, spatial/time resolution, domain, and update cadence for one dynamical.org dataset. dynamical.org/catalog is itself rendered from this same STAC catalog, so this tool fetches the collection document live (short TTL cache) rather than relying on anything baked into this server -- it's always as fresh as the STAC catalog itself. Args: collection_id: A STAC collection id, e.g. "noaa-gfs-forecast", "noaa-hrrr-analysis", or "ecmwf-aifs-ens-forecast". Use search_catalog to discover ids. Returns: A dict with title/model name, prose descriptions, spatial and time domain/resolution, forecast range (for forecast datasets), license and attribution, the dataset's variables, and links to its docs page and example notebooks. Raises ValueError (listing valid ids) if collection_id is unknown.
| Parameter | Type | Description |
|---|---|---|
| collection_id * | string |
{
"name": "get_dataset_info",
"title": "Get dataset details",
"description": "Get documentation, spatial/time resolution, domain, and update cadence\nfor one dynamical.org dataset.\n\ndynamical.org/catalog is itself rendered from this same STAC catalog, so\nthis tool fetches the collection document live (short TTL cache) rather\nthan relying on anything baked into this server -- it's always as fresh\nas the STAC catalog itself.\n\nArgs:\n collection_id: A STAC collection id, e.g. \"noaa-gfs-forecast\",\n \"noaa-hrrr-analysis\", or \"ecmwf-aifs-ens-forecast\". Use\n search_catalog to discover ids.\n\nReturns:\n A dict with title/model name, prose descriptions, spatial and time\n domain/resolution, forecast range (for forecast datasets), license\n and attribution, the dataset's variables, and links to its docs\n page and example notebooks. Raises ValueError (listing valid ids)\n if collection_id is unknown.\n",
"inputSchema": {
"type": "object",
"title": "get_dataset_infoArguments",
"required": [
"collection_id"
],
"properties": {
"collection_id": {
"type": "string",
"title": "Collection Id"
}
}
},
"outputSchema": {
"type": "object",
"title": "get_dataset_infoDictOutput",
"additionalProperties": true
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true
}
}Check run freshness and arrival status for a dynamical.org forecast dataset, from the same public feed status.dynamical.org's dashboard polls. Only forecast collections are pipeline-monitored today (analysis collections like noaa-gfs-analysis or noaa-mrms-conus-analysis-hourly aren't yet tracked by this feed). Args: collection_id: A STAC collection id, e.g. "noaa-gfs-forecast". limit: Maximum number of recent runs to return, most recent first (default 10). Returns: A dict with the overall pipeline `sla_status`, this product's cadence and next expected init/completion time, typical latency stats, and up to `limit` recent runs (`init_time`, `status`, `completion_pct`, `on_timedness`, arrival/latency timestamps). If collection_id isn't pipeline-monitored, returns `monitored`: False plus the list of collection ids that are.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | |
| collection_id * | string |
{
"name": "list_recent_runs",
"title": "List recent forecast runs",
"description": "Check run freshness and arrival status for a dynamical.org forecast\ndataset, from the same public feed status.dynamical.org's dashboard polls.\n\nOnly forecast collections are pipeline-monitored today (analysis\ncollections like noaa-gfs-analysis or noaa-mrms-conus-analysis-hourly\naren't yet tracked by this feed).\n\nArgs:\n collection_id: A STAC collection id, e.g. \"noaa-gfs-forecast\".\n limit: Maximum number of recent runs to return, most recent first\n (default 10).\n\nReturns:\n A dict with the overall pipeline `sla_status`, this product's\n cadence and next expected init/completion time, typical latency\n stats, and up to `limit` recent runs (`init_time`, `status`,\n `completion_pct`, `on_timedness`, arrival/latency timestamps). If\n collection_id isn't pipeline-monitored, returns `monitored`: False\n plus the list of collection ids that are.\n",
"inputSchema": {
"type": "object",
"title": "list_recent_runsArguments",
"required": [
"collection_id"
],
"properties": {
"limit": {
"type": "integer",
"title": "Limit",
"default": 10
},
"collection_id": {
"type": "string",
"title": "Collection Id"
}
}
},
"outputSchema": {
"type": "object",
"title": "list_recent_runsDictOutput",
"additionalProperties": true
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true
}
}Search dynamical.org's STAC catalog of cloud-optimized weather and climate datasets. Matches against each dataset's model name, description, spatial/time domain and resolution, forecast range, and variable names -- so a query can be a model ("GFS"), a variable ("precipitation", "temperature_2m"), a region ("continental US", "global"), or a resolution ("3km", "0.25 degree"). Results are ranked by number of matching terms. Args: query: Free-text search terms, e.g. "hourly precipitation CONUS" or "ECMWF ensemble forecast". limit: Maximum number of results to return (default 5). Returns: {"query": ..., "results": [{"collection_id", "title", "model_name", "description_summary", "spatial_domain", "spatial_resolution", "matched_variables", "score"}, ...]}, most relevant first. Pass a result's collection_id to get_dataset_info, get_access_pattern, or list_recent_runs.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | |
| query * | string |
{
"name": "search_catalog",
"title": "Search weather & climate catalog",
"description": "Search dynamical.org's STAC catalog of cloud-optimized weather and\nclimate datasets.\n\nMatches against each dataset's model name, description, spatial/time\ndomain and resolution, forecast range, and variable names -- so a query\ncan be a model (\"GFS\"), a variable (\"precipitation\", \"temperature_2m\"),\na region (\"continental US\", \"global\"), or a resolution (\"3km\", \"0.25\ndegree\"). Results are ranked by number of matching terms.\n\nArgs:\n query: Free-text search terms, e.g. \"hourly precipitation CONUS\"\n or \"ECMWF ensemble forecast\".\n limit: Maximum number of results to return (default 5).\n\nReturns:\n {\"query\": ..., \"results\": [{\"collection_id\", \"title\", \"model_name\",\n \"description_summary\", \"spatial_domain\", \"spatial_resolution\",\n \"matched_variables\", \"score\"}, ...]}, most relevant first. Pass a\n result's collection_id to get_dataset_info, get_access_pattern, or\n list_recent_runs.\n",
"inputSchema": {
"type": "object",
"title": "search_catalogArguments",
"required": [
"query"
],
"properties": {
"limit": {
"type": "integer",
"title": "Limit",
"default": 5
},
"query": {
"type": "string",
"title": "Query"
}
}
},
"outputSchema": {
"type": "object",
"title": "search_catalogDictOutput",
"additionalProperties": true
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true
}
}Tools for discovering and using dynamical.org's public STAC catalog of cloud-optimized weather and climate datasets: search for datasets by model/variable/region/resolution, look up a dataset's docs and update cadence, get a ready-to-run code snippet for opening its data, and check recent forecast-run freshness.
Names, descriptions and schemas were written by the server and are shown as data.