search_datasets
Pack: arcgis-hub · Endpoint: https://gateway.pipeworx.io/arcgis-hub/mcp
No MCP client? Call it directly: GET https://gateway.pipeworx.io/v1/tools/search_datasets for the schema, then POST the same URL with its arguments for the data.
Search the ArcGIS Hub catalog of open government geospatial datasets by keyword. Optionally scope to one organization with org_id (an ArcGIS orgId). Returns each dataset’s name, summary, record_count, owner/org, and its Feature Service url — pass that url to query_layer / layer_info.
Parameters
| Name | Type | Required | Description |
|---|---|---|---|
query | string | no | Keyword(s), e.g. “parcels”, “crime”, “flood zones”. |
org_id | string | no | Optional ArcGIS orgId to scope results to one publisher (e.g. “RmCCgQtiZLDCtblq” = LA County). |
limit | number | no | Max datasets (1-50, default 20). |
Example call
Arguments
{
"query": "parcels"
}curl
curl -X POST https://gateway.pipeworx.io/arcgis-hub/mcp \
-H 'Content-Type: application/json' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"search_datasets","arguments":{"query":"parcels"}}}'TypeScript (@pipeworx/sdk)
import { Pipeworx } from '@pipeworx/sdk';
const pipeworx = new Pipeworx();
const result = await pipeworx.call('search_datasets', {
"query": "parcels"
});More examples
{
"query": "crime incidents",
"org_id": "RmCCgQtiZLDCtblq",
"limit": 10
}Connect
Add this to your MCP client config, or use one-click install buttons:
{
"mcpServers": {
"arcgis-hub": {
"url": "https://gateway.pipeworx.io/arcgis-hub/mcp"
}
}
}See Getting Started for client-specific install steps.