# dynamical.org Weather & Climate Catalog MCP server

Search dynamical.org's open STAC catalog of weather & climate datasets (GFS, ECMWF, HRRR).

## Links
- Registry page: https://www.getdrio.com/mcp/io-github-dynamical-org-mcp
- Website: https://dynamical.org

## Install
- Endpoint: https://mcp.dynamical.org/mcp
- Auth: Not captured

## Setup notes
- Remote endpoint: https://mcp.dynamical.org/mcp

## Tools
- get_access_pattern (Get data access snippet) - 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.
 Endpoint: https://mcp.dynamical.org/mcp
- get_dataset_info (Get dataset details) - 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.
 Endpoint: https://mcp.dynamical.org/mcp
- list_recent_runs (List recent forecast runs) - 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.
 Endpoint: https://mcp.dynamical.org/mcp
- search_catalog (Search weather & climate catalog) - 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.
 Endpoint: https://mcp.dynamical.org/mcp

## Resources
Not captured

## Prompts
Not captured

## Metadata
- Owner: io.github.dynamical-org
- Version: 0.1.1
- Runtime: Streamable Http
- Transports: HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: Jul 6, 2026
- Source: https://registry.modelcontextprotocol.io