How to Use the Wikidata MCP in Claude

Q: How does Wikidata interact with Claude Desktop for data retrieval?

The MCP Server exposes several tools, like executesparql and getitem, that your AI agent calls directly. This lets Claude Desktop bypass traditional APIs and pull structured graph data into the chat output.

Q: Can I use Wikidata to calculate similarity scores with Claude Desktop?

Yep, you can use getsimilarityscore against text and an entity. This tool computes how close two pieces of information are, helping your agent understand context that standard keyword searches miss.

Q: What happens if my SPARQL query times out using Wikidata with Claude Desktop?

The documentation suggests passing a specific hint to executesparql. You should try setting the 'Query hint:optimizer' to 'None' if your queries are timing out.

Query structured knowledge graphs directly from your Claude Desktop agent.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Wikidata MCP to Claude Desktop

Create your Vinkius account to connect Wikidata to Claude Desktop and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Wikidata with Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run complex graph queries on Wikidata

Use `execute_sparql` to run arbitrary SPARQL queries against the world's largest open knowledge graph. You pass the query, and your AI client gets back structured results immediately. Need details about a single item? Call `get_item(g., Q42)` via the Wikibase REST API to pull specific Wikidata Item data directly into Claude Desktop.

Find items using vector search

Don't rely on keyword matching. Use `search_items_vector` for hybrid vector and keyword searches across all Wikidata Items. This means you can find things based on meaning, not just exact words. If you need to narrow down what kind of thing you're looking for, try `search_properties_vector`. It runs the same powerful search against the data type (Properties) associated with the items.

Manage item details and statements

Need to add new structured facts? The `create_statement` tool lets you build a new statement for an Item, provided you pass your OAuth 2.0 Access Token. It's direct data manipulation through the MCP Server. If you just need to check existing facts or update descriptions, use `get_item_statements` or call `set_item_description`. These tools manage the actual structured records.

Setup guide

Set up Wikidata MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The Wikidata MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the Wikidata MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under wikidata-mcp.

json

{
  "mcpServers": {
    "wikidata-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Wikidata. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Wikidata now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Wikidata MCP in Claude Desktop

The MCP Server exposes several tools, like `execute_sparql` and `get_item`, that your AI agent calls directly. This lets Claude Desktop bypass traditional APIs and pull structured graph data into the chat output.

Yep, you can use `get_similarity_score` against text and an entity. This tool computes how close two pieces of information are, helping your agent understand context that standard keyword searches miss.

This server handles structured knowledge graph data, including Item statements and Property definitions. The specific types include strings, URIs, and various resource relationships defined by Wikidata.

You set it up in the local stdio server configuration file within your Claude Desktop settings. You add the MCP Server details there and fully restart the app so the agent can see the tools.

The documentation suggests passing a specific hint to `execute_sparql`. You should try setting the 'Query hint:optimizer' to 'None' if your queries are timing out.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript