How to Use the Wikidata MCP in OpenAI Agents SDK

Q: How does the OpenAI Agents SDK handle Wikidata data retrieval?

The agents auto-discover all available tools, including getitem and executesparql. When you pass the MCP Server to the Agent constructor, your agent knows exactly how to query entities via SPARQL without needing special setup.

Q: What happens if a SPARQL query times out when using Wikidata with OpenAI Agents SDK?

The server provides a helpful hint: use query hint:optimizer "None" within the executesparql call. This prevents timeouts by forcing the optimizer to skip certain checks, letting you get your data faster.

Q: Can I search for properties using Wikidata and OpenAI Agents SDK?

Yeah, of course. The searchpropertiesvector tool lets you run a hybrid vector/keyword search specifically across the Properties in Wikidata. This is perfect when you're looking for metadata attributes rather than whole items.

Q: Does the OpenAI Agents SDK support complex data updates on Wikidata?

Yes, it supports updating structured records using createstatement and setitemdescription. Since these functions require an OAuth 2.0 Access Token, your agent's actions are always authenticated.

Q: What type of data does the MCP Server touch when setting descriptions for Wikidata with OpenAI Agents SDK?

The setitemdescription tool writes to and manages structured text data associated with a specific Item's record. This involves handling descriptive strings, which are key parts of the knowledge graph.

Build production agents that query structured knowledge graphs using the OpenAI Agents SDK.

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 OpenAI Agents SDK

Create your Vinkius account to connect Wikidata to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute complex queries with `execute_sparql`.

Run arbitrary SPARQL queries against Wikidata. Your agent directly executes `execute_sparql`, pulling back results that match your query structure. You avoid writing custom database connectors; the MCP Server handles the heavy lifting, letting you focus on the logic.

Use `search_items_vector` for precise knowledge lookup.

Need to find an item when keywords aren't enough? The `search_items_vector` tool performs a hybrid vector and keyword search. It lets your agent pinpoint items by semantic meaning, not just exact matches.

Manage structured data with `set_item_description`.

`set_item_description` allows you to write or update the description for a specific Wikidata Item. Because this tool requires an OAuth 2.0 Access Token, it ensures your agent acts only with proper credentials. This makes updating knowledge base details reliable and trackable.

Setup guide

Set up Wikidata MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Wikidata tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Wikidata tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Wikidata tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Wikidata Agent",
            instructions="You have access to Wikidata tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

The agents auto-discover all available tools, including `get_item` and `execute_sparql`. When you pass the MCP Server to the Agent constructor, your agent knows exactly how to query entities via SPARQL without needing special setup.

The server provides a helpful hint: use `query hint:optimizer "None"` within the `execute_sparql` call. This prevents timeouts by forcing the optimizer to skip certain checks, letting you get your data faster.

Yeah, of course. The `search_properties_vector` tool lets you run a hybrid vector/keyword search specifically across the Properties in Wikidata. This is perfect when you're looking for metadata attributes rather than whole items.

Yes, it supports updating structured records using `create_statement` and `set_item_description`. Since these functions require an OAuth 2.0 Access Token, your agent's actions are always authenticated.

The `set_item_description` tool writes to and manages structured text data associated with a specific Item's record. This involves handling descriptive strings, which are key parts of the knowledge graph.

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