How to Use the Wikidata MCP in Claude Code

Q: How do I run a complex query against Wikidata using Claude Code?

You invoke executesparql directly from your terminal. The output is piped as standard text, making it easy to consume the structured data in subsequent shell scripts or actions.

Q: Can I search for entities programmatically using Wikidata and Claude Code?

Yes. You can use searchitemsvector and searchpropertiesvector. These tools handle hybrid searches, giving your script the flexibility to find records based on keywords or vector embeddings.

Q: What is the most reliable way to fetch item data using Wikidata and Claude Code?

For a comprehensive record of facts, run getitemstatements. This ensures your script captures every single statement associated with that Item in the open knowledge graph.

Q: Does this MCP Server allow me to write data back to Wikidata from my scripts?

Yep. You use createstatement for writing new statements, but remember you must provide an OAuth 2.0 Access Token for the operation to succeed.

Automate Wikidata data pipelines with Claude Code: Headless execution for your CI/CD workflows.

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 Code

Create your Vinkius account to connect Wikidata to Claude Code 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 Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

MCP Server: Scheduled Data Extraction

Run a SPARQL query against Wikidata from a shell script or GitHub Action. Use `execute_sparql` to pull structured data, pipe it directly into another tool, and process it without needing any GUI or browser context. This makes running nightly data dumps reliable. If the queries time out, you can programmatically adjust the hint using 'None' for the optimizer.

Automated Item Lookup

Need to confirm an item ID? Use `get_item` via the Wikibase REST API. This function retrieves essential details about a specific Wikidata Item, letting your script validate inputs or pull base data for processing. It's perfect for pre-flight checks in any automated pipeline.

Mass Data Discovery and Modification

For complex tasks, Claude Code supports both reading and writing. You can run `search_items_vector` or `search_properties_vector` to find data programmatically, then use `create_statement` to write new records back to Wikidata. This requires an OAuth 2.0 Access Token. It turns multi-step research into a single, reliable pipeline command.

Setup guide

Set up Wikidata MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see wikidata-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Wikidata transactions." It will automatically discover and invoke the available Wikidata tools.

Terminal

claude mcp add --transport http wikidata-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Wikidata MCP

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

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "wikidata-mcp": {
      "type": "url",
      "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 Code

You invoke `execute_sparql` directly from your terminal. The output is piped as standard text, making it easy to consume the structured data in subsequent shell scripts or actions.

Yes. You can use `search_items_vector` and `search_properties_vector`. These tools handle hybrid searches, giving your script the flexibility to find records based on keywords or vector embeddings.

For a comprehensive record of facts, run `get_item_statements`. This ensures your script captures every single statement associated with that Item in the open knowledge graph.

Yep. You use `create_statement` for writing new statements, but remember you must provide an OAuth 2.0 Access Token for the operation to succeed.

This MCP Server operates on public, structured 'statements' (triples) from the world's open knowledge graph. All output is standard text, ideal for piping.

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