@pipeworx/wikidata-sparql

Connect: https://gateway.pipeworx.io/wikidata-sparql/mcp · Install: one-click buttons

Tools: 5

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.

Tools

• query — Run a SPARQL query against the Wikidata Query Service. Returns JSON bindings by default.
• instances_of — Convenience: list all items that are an instance of a Wikidata class.
• subclasses_of — Convenience: subclass tree (P279 transitive) of a class.
• properties_of — Convenience: all statements (property → value) about an entity.
• entities_at — Geo-spatial query: items near a point. Use instance_of to filter by class.