`knmi_datasets`

Pack: knmi · Endpoint: https://gateway.pipeworx.io/knmi/mcp

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

The KNMI Data Platform datasets worth calling, with what each one contains, how often it updates and its file format — and, checked live, the timestamp of its newest file. AUTHORITATIVE starting point for Dutch weather and climate data: KNMI is the Netherlands national weather service. Use this to find the exact dataset name and version string that knmi_dataset_files needs, because those names are opaque (e.g. “Tg1”, “EV24”, “harmonie_arome_cy43_p1”) and the Open Data API has no listing endpoint of its own. Search for “radar”, “observations”, “forecast”, “precipitation”, “temperature”, “evaporation”.

Parameters

Name	Type	Required	Description
`search`	string	no	Case-insensitive substring matched against dataset name and description, e.g. “radar”.
`verify`	boolean	no	Check each matched dataset live and report its newest file and timestamp (default true). Set false to skip the upstream calls and just read the registry.
`limit`	number	no	Max datasets to return (default 5, max 11). Each one costs an upstream call when verify is true.

Example call

Arguments

{
  "search": "radar"
}

curl

curl -X POST https://gateway.pipeworx.io/knmi/mcp \
  -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"knmi_datasets","arguments":{"search":"radar"}}}'

TypeScript (@pipeworx/sdk)

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

const result = await pipeworx.call('knmi_datasets', {
  "search": "radar"
});

More examples

{
  "search": "observations",
  "limit": 2
}

Connect

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

{
  "mcpServers": {
    "knmi": {
      "url": "https://gateway.pipeworx.io/knmi/mcp"
    }
  }
}

See Getting Started for client-specific install steps.

knmi_datasets