recherche.data.gouv.fr MCP demo

Tools

• recherche_data_gouv_mcp_get_collection Retrieve one Recherche Data Gouv (Dataverse) collection by alias or numeric id. Returns: {"source": "recherche-data-gouv", "command": "get_collection", "identifier": str, "total_found": int | null, "returned": int, "results": [{"source": str, "type": "dataverse", "id": str, "alias": str, "name": str, "affiliation": str | null, "description": str | null, "url": str, "parent_alias": str | null, "dataset_count": int | null, "subcollection_count": int | null}], "error": str | null}
• recherche_data_gouv_mcp_get_dataset Retrieve the latest published version of one dataset by its persistent id. The canonical server also offers an include_raw switch that attaches the untouched upstream payload; this demo always omits it, because that payload embeds every metadata block and the whole file list. Returns: {"source": "recherche-data-gouv", "command": "get_dataset", "persistent_id": str, "total_found": int | null, "returned": int, "results": [{"source": str, "type": "dataset", "id": str, "title": str, "authors": [{"authorName": str, "authorAffiliation": str | null}], "description": str | null, "subjects": [str], "keywords": [str], "url": str, "version": str, "license": str | null, "file_count": int, "metadata_blocks": [str]}], "error": str | null}
• recherche_data_gouv_mcp_list_collection_contents List the direct children of a collection: its sub-collections and its datasets. One hop down the tree, not the whole sub-tree. The upstream endpoint neither paginates nor honours a limit, so max_items clamps the answer here and total_found reports the untruncated count. Dataset entries carry a DOI but no title, and sub-collection entries a numeric id but no alias: feed either back into get_dataset or get_collection. This demo caps max_items at 25. Returns: {"source": "recherche-data-gouv", "command": "list_collection_contents", "identifier": str, "item_type": str | null, "total_found": int, "returned": int, "truncated": bool, "results": [{"source": str, "type": str, "id": str, "persistent_id": str | null, "title": str | null, "url": str | null, "publication_date": str | null}], "error": str | null}
• recherche_data_gouv_mcp_list_dataset_files List the files of one dataset version, with sizes, checksums and download URLs. Like the collection listing, the upstream endpoint neither paginates nor honours a limit, so max_items clamps the answer here and total_found reports the untruncated count. This demo caps max_items at 25. download_url is the public bytes endpoint; nothing here fetches it. Returns: {"source": "recherche-data-gouv", "command": "list_dataset_files", "persistent_id": str, "version": str, "total_found": int, "returned": int, "truncated": bool, "total_size_bytes": int, "results": [{"source": str, "type": "file", "id": int, "filename": str, "content_type": str, "size_bytes": int, "restricted": bool, "download_url": str, "checksum": str | null}], "error": str | null}
• recherche_data_gouv_mcp_metadatablocks List the Dataverse metadata blocks of Recherche Data Gouv, or retrieve one block schema. Returns: {"source": "recherche-data-gouv", "command": "metadatablocks", "block": str | null, "data": object, "error": str | null}
• recherche_data_gouv_mcp_metrics Fetch a public Dataverse Metrics API counter for the whole Recherche Data Gouv instance. Returns: {"source": "recherche-data-gouv", "command": "metrics", "category": str, "breakdown": str | null, "data": object, "error": str | null}
• recherche_data_gouv_mcp_search Search public Recherche Data Gouv (Dataverse) records: datasets, dataverses and files. Returns: {"source": "recherche-data-gouv", "command": "search", "query_used": str, "total_found": int, "returned": int, "results": [{"source": str, "id": str, "type": str, "title": str, "authors": [str], "url": str, "published_at": str | null}], "error": str | null}

No tool matches.

As the server's own listing gives them. We never call a tool.