Wikidata MCP Connector for Claude

Connect to Wikidata, the central storage for structured data of Wikimedia projects. This MCP server allows your AI agent to tap into millions of items, properties, and statements using both traditional SPARQL queries and modern vector-based semantic search.

What you can do

• Entity Retrieval — Fetch full data and statements for any Wikidata Item (e.g., Q42) using the get_item and get_item_statements tools.
• Advanced Querying — Execute complex SPARQL queries against the Wikidata Query Service (WDQS) with execute_sparql to find relationships and patterns across the entire graph.
• Semantic Search — Use search_items_vector and search_properties_vector to find entities and properties based on meaning rather than just exact keywords.
• Data Contribution — Update the knowledge graph by creating statements or setting descriptions with create_statement and set_item_description (requires OAuth).
• Similarity Analysis — Compare text strings against specific entities to get semantic similarity scores using get_similarity_score.

How it works

1. Subscribe to this server
2. Provide your User Agent (required by Wikimedia policy)
3. Optionally provide an OAuth 2.0 Access Token for write operations
4. Start exploring the world's knowledge from your favorite AI client

Who is this for?

• Researchers & Academics — instantly verify facts, dates, and relationships across history, science, and culture.
• Data Scientists — extract structured datasets for analysis or training without leaving the chat interface.
• Developers — find entity IDs and property schemas to integrate into applications or automate data enrichment.