How to Use the Wikidata MCP in Google ADK

Q: How does Google ADK handle complex SPARQL queries on Wikidata?

The executesparql tool allows your agent to run any necessary query. You just pass the structured request, and the MCP Server executes it against Wikidata's graph. Your long-context Gemini models can then hold all those results for deep analysis.

Q: What is the best way to find an item using Google ADK on Wikidata?

If you know the Item ID, use getitem. If you're searching by concept or keyword, searchitemsvector is your go-to. The agent handles both methods seamlessly, providing maximum retrieval options.

Q: Can I manage Wikidata statements using Google ADK?

Absolutely. Tools like createstatement and setitemdescription let your agent write or update records on the graph. Because it's an enterprise setup, you know every action is logged and controlled.

Q: Does Wikidata support structured data updates with Google ADK?

Yes, managing statements through createstatement ensures your agent maintains high integrity when adding new facts. It's built for the kind of production scale that BigQuery expects.

Build enterprise agents that query Wikidata via Google ADK, integrating directly with BigQuery and Vertex AI.

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 Google ADK

Create your Vinkius account to connect Wikidata to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Retrieve item details using `get_item`.

`get_item` pulls structured data for a specific Wikidata Item ID (like Q42) via the Wikibase REST API. This makes it simple for your agent to pull core entity information into its long-context reasoning pipeline. You'll get clean, reliable records that you can then process in BigQuery or pass through Gemini models for advanced analysis.

Compare texts with `get_similarity_score`.

Need to know if two pieces of text are similar? The `get_similarity_score` tool calculates the relationship between a given string and an entity. It’s great for data cleaning tasks where you must verify user input against known records. This comparison mechanism gives your agent confidence scores, helping it decide if the source data is trustworthy enough to use.

Search across multiple dimensions with MCP Server.

Your agent can run deep searches using either `search_items_vector` or `search_properties_vector`. These tools handle a hybrid approach, mixing keyword matching with vector search. It means you find items by what they mean, not just what they contain. This capability makes the MCP Server incredibly versatile for data discovery across different types of knowledge.

Setup guide

Set up Wikidata MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Wikidata tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Wikidata_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Wikidata tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

The `execute_sparql` tool allows your agent to run any necessary query. You just pass the structured request, and the MCP Server executes it against Wikidata's graph. Your long-context Gemini models can then hold all those results for deep analysis.

If you know the Item ID, use `get_item`. If you're searching by concept or keyword, `search_items_vector` is your go-to. The agent handles both methods seamlessly, providing maximum retrieval options.

Absolutely. Tools like `create_statement` and `set_item_description` let your agent write or update records on the graph. Because it's an enterprise setup, you know every action is logged and controlled.

Yes, managing statements through `create_statement` ensures your agent maintains high integrity when adding new facts. It's built for the kind of production scale that BigQuery expects.

The server primarily touches structured descriptive text and relationships, specifically managing the content passed via `create_statement` and setting new metadata records for an Item.

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