`cds_collections`

Pack: copernicus-cds · Endpoint: https://gateway.pipeworx.io/copernicus-cds/mcp

No MCP client? Call it directly: GET https://gateway.pipeworx.io/v1/tools/cds_collections for the schema, then POST the same URL with its arguments for the data.

List or keyword-search the Copernicus Climate Data Store catalogue — the ~140 published climate datasets (ERA5 reanalysis, CMIP6/CORDEX projections, satellite ECVs, seasonal forecasts, in-situ networks). Returns each collection id (pass it to cds_collection or cds_submit_request), title, and the temporal/spatial extent it covers. Keyless. AUTHORITATIVE for “which Copernicus/C3S dataset covers X” — the catalogue itself, not a description of it.

Parameters

Name	Type	Required	Description
`query`	string	no	Optional keyword filter, matched against collection id, title and description (e.g. “sea ice”, “ERA5”, “wildfire”). Omit to list everything.
`limit`	number	no	Max collections to return (1-200, default 25).
`offset`	number	no	Skip this many matches (default 0).

Example call

Arguments

{
  "query": "sea ice",
  "limit": 5
}

curl

curl -X POST https://gateway.pipeworx.io/copernicus-cds/mcp \
  -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"cds_collections","arguments":{"query":"sea ice","limit":5}}}'

TypeScript (@pipeworx/sdk)

import { Pipeworx } from '@pipeworx/sdk';
const pipeworx = new Pipeworx();

const result = await pipeworx.call('cds_collections', {
  "query": "sea ice",
  "limit": 5
});

More examples

{
  "query": "ERA5",
  "limit": 10
}

Connect

Add this to your MCP client config, or use one-click install buttons:

{
  "mcpServers": {
    "copernicus-cds": {
      "url": "https://gateway.pipeworx.io/copernicus-cds/mcp"
    }
  }
}

See Getting Started for client-specific install steps.

cds_collections