How to Use the Wikidata MCP in LangChain

Q: How do I find an Item using Wikidata and LangChain?

You use the searchitemsvector tool. Your agent runs a hybrid search, combining keywords with vector similarity against the world's largest open knowledge graph. This gives you multiple candidate IDs to work with.

Q: Can I get detailed facts for a Wikidata Item using LangChain?

Yes, call getitemstatements. This tool retrieves all associated statements for an item ID. Your agent can then process these raw data points and feed them into the next step of your reasoning chain.

Build complex, multi-step reasoning pipelines using Wikidata with LangChain.

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 LangChain

Create your Vinkius account to connect Wikidata to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Write structured data directly

Need to add a fact? Use `create_statement` and provide an OAuth 2.0 Access Token. This tool lets your agent write new, verifiable statements for any Wikidata Item. This capability is key when your workflow requires persistence. It moves the process beyond reading data into actually updating the structured knowledge graph.

Run advanced SPARQL queries

The `execute_sparql` tool lets you fire off specific, complex queries against Wikidata. You can use a query hint like `optimizer "None"` if standard queries time out, which is super helpful for debugging. This gives your agent granular control over the data retrieval process. It's better than just searching; it runs code against the graph.

Find items and properties via search

Start by narrowing down what you need using vector searches. Run `search_items_vector` for hybrid keyword/vector lookups, or use `search_properties_vector` to find relevant attributes. Once you have a candidate item ID, your agent can follow up by calling `get_item_statements` to fetch all associated facts about that specific entity.

Setup guide

Set up Wikidata MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Wikidata tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "wikidata-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Wikidata transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

You use the `search_items_vector` tool. Your agent runs a hybrid search, combining keywords with vector similarity against the world's largest open knowledge graph. This gives you multiple candidate IDs to work with.

You handle structured data: specific statements, item descriptions (`set_item_description`), and properties. Because your agent calls `execute_sparql`, it can pull nearly any type of relationship defined in the graph.

Yes, call `get_item_statements`. This tool retrieves all associated statements for an item ID. Your agent can then process these raw data points and feed them into the next step of your reasoning chain.

Absolutely. The MCP Server provides tools that let your agent read, search, and even write to the structured data of Wikidata. It treats the entire graph as an API endpoint within your multi-step pipeline.

This server touches structured statements and item descriptions. When you call `create_statement` or `set_item_description`, your agent requires an OAuth 2.0 Access Token, ensuring controlled write access to the data.

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