How to Use the Wikidata MCP in Cursor

Q: Can I use Wikidata's vector search features in Cursor?

Absolutely. The AI can run both searchitemsvector and searchpropertiesvector. This lets you ground your coding decisions in highly relevant, semantically searched knowledge graph data.

Q: If I need to check an item's existing facts using Wikidata in Cursor, what tool do I use?

You call getitemstatements. This retrieves a list of all statements associated with a specific Item ID. The AI then processes that list and gives you the structured data you need for your code.

Q: What happens if I forget to pass the OAuth token when calling Wikidata from Cursor?

Tools like createstatement require an OAuth 2.0 Access Token to function, as they write data. If you don't provide it, the MCP Server call fails because it can't authenticate your changes.

Get live Wikidata data context directly into your Cursor code editor.

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 Cursor

Create your Vinkius account to connect Wikidata to Cursor 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 Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build code using structured graph queries

The `execute_sparql` tool lets the AI call Wikidata and run complex SPARQL queries. When the AI gets a result, it injects that live data directly into the function or variable you're writing. You don't get mock data here; if you ask for an Item's properties, the agent uses `get_item_statements` to pull real-world facts and writes code based on them.

Search Wikidata context inside your project

Need to find a reference item? Use `search_items_vector`. The AI calls this tool, gets back relevant items, and then you can use that data immediately in your code structure. If the search is about data categories rather than specific entities, run `search_properties_vector` to narrow down your scope. This keeps your context accurate.

Create or modify Wikidata records programmatically

The agent can manipulate structured data using tools like `create_statement`. If you need to add a new fact about an item, the AI calls this tool and handles passing the OAuth 2.0 Access Token. For updating descriptions, it uses `set_item_description`. This means your code isn't just reading; it can write back structured information through the MCP Server.

Setup guide

Set up Wikidata MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Wikidata MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Wikidata transactions." If the MCP tools are loaded correctly, Cursor will call the Wikidata tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/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 Cursor

When you activate Agent mode, the AI sees all available tools on the Wikidata MCP Server. It decides which tool to call (like `get_item`) and then injects the real-time API response directly into your file as working code.

Absolutely. The AI can run both `search_items_vector` and `search_properties_vector`. This lets you ground your coding decisions in highly relevant, semantically searched knowledge graph data.

The server handles structured records from Wikidata. This includes Item statements and Property definitions—essentially, complex relationships between entities that you can model in code.

You call `get_item_statements`. This retrieves a list of all statements associated with a specific Item ID. The AI then processes that list and gives you the structured data you need for your code.

Tools like `create_statement` require an OAuth 2.0 Access Token to function, as they write data. If you don't provide it, the MCP Server call fails because it can't authenticate your changes.

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