opendatasoft 5 tools

MCP server exposing 5 tools for opendatasoft.

Endpoint

This URL is a JSON-RPC 2.0 endpoint over HTTP. Issue POST requests with a JSON-RPC body. Browsers and search crawlers land here on GET.

POST https://gateway.pipeworx.io/opendatasoft/mcp
Content-Type: application/json

{"jsonrpc":"2.0","id":1,"method":"tools/list"}

Tools

• datasets — 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.
• dataset — Fetch schema and metadata for a single Opendatasoft dataset by dataset_id; returns field definitions, record count, and dataset description from the specified portal instance.
• records — Query records from an Opendatasoft dataset with optional keyword search, ODSQL WHERE/SELECT/GROUP BY/ORDER BY clauses, pagination, and projection; returns matching rows as JSON.
• facets — Retrieve distinct values and counts for a named facet field within an Opendatasoft dataset; useful for enumerating categories or filtering options before querying records.
• instance_info — Fetch catalog-level metadata for an Opendatasoft portal instance (total dataset count, themes, languages); defaults to public.opendatasoft.com.

Full documentation

Code samples (curl / TypeScript / one-click client install), schemas, and the live playground are on the pack page:
https://pipeworx.io/packs/opendatasoft/

About Pipeworx

Pipeworx is an open MCP gateway connecting AI agents to live data. pipeworx.io