datasets
Pack: opendatasoft · Connect: https://pipeworx.io/mcp (see Connect below for a single-pack URL)
No MCP client? Call it directly: GET https://gateway.pipeworx.io/v1/tools/datasets for the schema, then POST the same URL with its arguments for the data.
Search datasets on any Opendatasoft portal (default public.opendatasoft.com) by keyword, with optional sort and facet filters; returns dataset IDs, titles, and field summaries.
Parameters
| Name | Type | Required | Description |
|---|---|---|---|
instance | string | no | Default ${DEFAULT_INSTANCE}. |
q | string | no | |
rows | number | no | |
start | number | no | |
sort | string | no | |
facet | string | no | Comma-sep facets to include. |
Example call
Arguments
{
"q": "population",
"rows": 10
}
curl
curl -X POST https://gateway.pipeworx.io/opendatasoft/mcp \
-H 'Content-Type: application/json' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"datasets","arguments":{"q":"population","rows":10}}}'
TypeScript (@pipeworx/sdk)
import { Pipeworx } from '@pipeworx/sdk';
const pipeworx = new Pipeworx();
const result = await pipeworx.call('datasets', {
"q": "population",
"rows": 10
});
More examples
{
"instance": "public.opendatasoft.com",
"q": "climate",
"sort": "-modified",
"facet": "theme,license"
}
Response shape
| Field | Type | Description |
|---|---|---|
results | array | Array of dataset objects |
total_count | number | Total count of matching datasets |
facets | array | Facet aggregations if requested |
Full JSON Schema
{
"type": "object",
"description": "Search results for datasets",
"properties": {
"results": {
"type": "array",
"description": "Array of dataset objects",
"items": {
"type": "object",
"properties": {
"dataset_id": {
"type": "string",
"description": "Unique dataset identifier"
},
"name": {
"type": "string",
"description": "Dataset name"
},
"description": {
"type": "string",
"description": "Dataset description"
},
"theme": {
"type": "string",
"description": "Dataset theme/category"
},
"records_count": {
"type": "number",
"description": "Number of records in dataset"
},
"modified": {
"type": "string",
"description": "Last modification date"
}
}
}
},
"total_count": {
"type": "number",
"description": "Total count of matching datasets"
},
"facets": {
"type": "array",
"description": "Facet aggregations if requested",
"items": {
"type": "object"
}
}
}
}
Connect
Add this to your MCP client config — every tool in the catalog, including this one — or use one-click install buttons:
{
"mcpServers": {
"pipeworx": {
"url": "https://pipeworx.io/mcp"
}
}
}
Connect to just the opendatasoft pack
{
"mcpServers": {
"opendatasoft": {
"url": "https://gateway.pipeworx.io/opendatasoft/mcp"
}
}
}
See Getting Started for client-specific install steps.