@pipeworx/wikidata-sparql

Connect: https://pipeworx.io/mcp — every tool in the catalog, including @pipeworx/wikidata-sparql’s. Install: one-click buttons

No MCP client? Skip the connection: POST https://gateway.pipeworx.io/v1/tools/search_packs {"query":"..."} to find a tool below, GET /v1/tools/<name> for its schema, POST the same URL with arguments for the data — see For AI agents.

Tools: 0

Wikidata Query Service MCP — full SPARQL access to the entire Wikidata knowledge graph (~100M items, 1.5B statements). Complements the existing wikidata pack (which covers entity search + retrieval).

Tools

• query(sparql, format?) — run a SPARQL query
• instances_of(entity_id, limit?) — convenience: all instances of a class (e.g. Q5 = humans)
• subclasses_of(entity_id, limit?) — convenience: subclass tree
• properties_of(entity_id, limit?) — convenience: statements about an entity
• entities_at(latitude, longitude, radius_km?, instance_of?, limit?) — geo-spatial query: items near a point

No auth

The public WDQS at https://query.wikidata.org/sparql is keyless. Fair-use: ≤30 queries / min, ≤60 sec timeout per query. The pack sets a meaningful User-Agent (required by WMF policy).

Tips

Wikidata is enormous — narrow your queries! Use LIMIT, instance of filters, and language tags. Bring schema knowledge from https://www.wikidata.org/wiki/Wikidata:List_of_properties.