Wikidata:MCP
|
This page is a work in progress, not an article or policy, and may be incomplete and/or unreliable.
Please offer suggestions on the talk page. বাংলা | català | čeština | Deutsch | English | español | فارسی | suomi | français | עברית | हिन्दी | magyar | italiano | 日本語 | 한국어 | Lëtzebuergesch | latviešu | македонски | Bahasa Melayu | မြန်မာဘာသာ | norsk bokmål | Nederlands | ਪੰਜਾਬੀ | polski | پنجابی | português | português do Brasil | română | Scots | shqip | slovenščina | српски / srpski | svenska | Türkçe | русский | українська | 中文（简体） | +/− |
The Wikidata MCP provides a set of standardized tools that allow large language models (LLMs) to explore and query Wikidata programmatically. It is designed for agentic AI or AI workflows that need to search, inspect, and query Wikidata, without relying on hardcoded assumptions about its structure or content.
Model Context Protocol (MCP)
[edit]Model Context Protocol (MCP), often described as "USB-C for AI", is an open standard, open-source framework introduced by Anthropic to standardize the way large language models (LLMs) interact with external tools, systems, and data sources.
How to set up
[edit]The Wikidata MCP is available as an HTTP app at https://wd-mcp.wmcloud.org/
To use it, add https://wd-mcp.wmcloud.org/mcp/ as a connector in your AI client.
Code
[edit]The code for the Wikidata MCP is a work in progress and can be found in this Github repository.
Tools
[edit]Here's the list of tool that the MCP provides to the AI models:
- Vector Search Items: Performs semantic search over Wikidata items using vector embeddings, querying the Wikidata vector database developed under the Wikidata Embedding Project
- Vector Search Properties: Performs semantic search over Wikidata properties, querying the Wikidata vector database developed under the Wikidata Embedding Project
- Keyword Search Items: Performs exact keyword search across Wikidata item labels, aliases, and descriptions using the Wikidata Action API.
- Keyword Search Properties: Performs exact keyword search across Wikidata properties labels, aliases, and descriptions using the Wikidata Action API.
- Get Entity Claims: Lists all direct graph connections (statements) of a Wikidata entity in triplet format, including claim values and their qualifiers.
- Get Claim Values: Get all values for a specific claim (entity-property pair) and retrieve complete statements including deprecated values and reference data that are excluded from the Get Entity Claims tool.
- Execute SPARQL: Executes any SPARQL query against Wikidata and returns results as a CSV table, or error messages if the query fails.
Presentations & blog posts
[edit]- "Wikidata MCP: Exploring Wikidata with AI" - presentation by Philippe Saadé of Wikimedia Deutschland at WikidataCon 2025, Nov 2, 2025 (slides, Etherpad Notes)