An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Wikidata to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Pull facts and relationships from the world's largest open database.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 8 capabilities

We ship only the actions that matter.

Capability set01 / 02

01-04

4 capabilities in this set.

Part of 8 available through Wikidata.

  1. 01

    Search properties vector

    This capability performs hybrid vector and keyword searches to find specific Wikidata properties. It's useful when you need to find a property based on its meaning rather than a strict name.

  2. 02

    Set item description

    Use this capability to update an item's description in Wikidata. This requires an OAuth 2.0 Access Token.

  3. 03

    Get item statements

    This capability retrieves all the specific statements associated with a given Wikidata Item. It's the fastest way to see the facts tied to an entity.

  4. 04

    Execute sparql

    This capability runs complex SPARQL queries against the Wikidata Query Service. If a query is taking too long, you can pass a hint to disable the optimizer.

Capability set02 / 02

05-08

4 capabilities in this set.

Part of 8 available through Wikidata.

  1. 05

    Create statement

    This capability allows you to add new statements to a Wikidata Item. You will need an OAuth 2.0 Access Token to use this.

  2. 06

    Get item

    This capability fetches the full data for a specific Wikidata Item using its unique ID. It uses the Wikibase REST API to get the job done.

  3. 07

    Get similarity score

    Use this capability to calculate how similar a piece of text is to a specific entity. It's great for verifying if your agent is talking about the right thing.

  4. 08

    Search items vector

    This capability uses hybrid vector and keyword search to find items in the knowledge graph. It helps your agent find entities even when the exact name is unknown.

Real work

What teams actually run

01

Fact Verification

An agent checks a specific Wikidata item to confirm a person's birth date or occupation.

02

Dataset Extraction

A user runs a SPARQL query to pull a list of all countries in a specific continent.

03

Semantic Mapping

An agent uses vector search to find related concepts when a user provides a vague description.

04

Knowledge Maintenance

A contributor uses the MCP to update an item's description or add a missing statement.

Automate a task

Put Wikidata to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Wikidata works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Wikidata to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

963ms average. Fast in production.

Wikidata is checked daily against the live service.

Daily averagePeak 1190ms
Oct 3Today
Fastest day
720ms
Slowest day
1190ms
14-day trend
Stable0%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 8 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Wikidata, so you can see the experience inside your AI.

It does not authenticate your account with Wikidata. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Wikidata Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_W84JNbFgMiFDqgSOAzXVMSCHncfEanhMXyqzOlEz/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Wikidata capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "wikidata-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_W84JNbFgMiFDqgSOAzXVMSCHncfEanhMXyqzOlEz/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Wikidata in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Wikidata owners hand off.

This MCP is built for anyone who needs to ground their AI agent in verified, structured facts.

  • 01

    Researchers

    They use the agent to verify historical dates and scientific relationships.

  • 02

    Data Scientists

    They extract structured datasets for analysis without manual scraping.

  • 03

    Developers

    They use the capabilities to find entity IDs and property schemas for their own apps.

FAQ

Questions Wikidata owners ask.

  • 01

    Do I need special permissions to edit Wikidata?

    Yes, writing data like new statements or descriptions requires an OAuth 2.0 Access Token.

  • 02

    What is the difference between the search capabilities?

    The vector search capabilities find items or properties based on semantic meaning, while SPARQL is used for structured, logic-based queries.

  • 03

    How do I provide my identity to Wikimedia?

    You must provide a User Agent string to comply with Wikimedia's data access policies.

  • 04

    Can I use this with any AI client?

    Yes, this MCP works with any client that supports the Model Context Protocol, such as Claude, Cursor, or Windsurf.

  • 05

    What happens if my SPARQL query times out?

    You can use a specific query hint to set the optimizer to 'None' to help the query complete.

  • 06

    How can I find a Wikidata Item if I don't know its Q-ID?

    You can use the search_items_vector capability. It performs a hybrid search using high-dimensional embeddings and keywords to find the most relevant entities based on your natural language description.

  • 07

    Is it possible to run complex queries like 'List all female scientists born in the 19th century'?

    Yes, the execute_sparql capability allows you to run any valid SPARQL query against the Wikidata Query Service. This is the most powerful way to filter and aggregate data across the entire knowledge graph.

  • 08

    Can I use this server to update information on Wikidata?

    Yes, if you provide an OAuth 2.0 Access Token, you can use create_statement to add new data or set_item_description to update descriptions in various languages.

Explore

More in The Unthinkable

Suggestions

Connect Wikidata to Claude, Cursor, ChatGPT & more