`search_datasets`

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

Search the Humanitarian Data Exchange catalogue (CKAN package_search) for datasets on displacement, refugees, food security, conflict, disasters, health, population, etc. Returns matching datasets with titles, descriptions, publishing organization, locations (groups), and resources. Filter by country/crisis with fq=“groups:” (e.g. “groups:syr”) — get codes from list_locations.

Parameters

Name	Type	Required	Description
`query`	string	yes	Search terms, e.g. “displacement”, “food security”, “conflict fatalities”.
`fq`	string	no	Solr filter query (facet filter). e.g. “groups:syr” (location = Syria), “organization:unhcr”, “res_format:CSV”. Combine with spaces.
`rows`	number	no	Max results, 1-1000 (default 25).
`start`	number	no	0-based offset for paging.
`sort`	string	no	Sort spec, e.g. “metadata_modified desc” or “score desc”.

Example call

Arguments

{
  "query": "displacement refugees"
}

curl

curl -X POST https://gateway.pipeworx.io/hdx/mcp \
  -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"search_datasets","arguments":{"query":"displacement refugees"}}}'

TypeScript (@pipeworx/sdk)

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

const result = await pipeworx.call('search_datasets', {
  "query": "displacement refugees"
});

More examples

{
  "query": "food security",
  "fq": "groups:syr",
  "rows": 50,
  "sort": "metadata_modified desc"
}

Connect

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

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

See Getting Started for client-specific install steps.

search_datasets