How to Use the Wikidata MCP in Pydantic AI

Q: How does Pydantic AI manage SPARQL results from Wikidata?

The executesparql tool runs the query. Then, Pydantic AI intercepts the raw data and validates it against your defined models at runtime. If the result doesn't match, you get a clear validation error—you don't get garbage.

Q: What search methods are available for Wikidata with Pydantic AI?

You have three main options: searchitemsvector (for semantic item lookup), searchpropertiesvector (for metadata attributes), or running a precise SPARQL query via the MCP Server. They all feed into your type-safe workflow.

Q: Can I retrieve specific Wikidata items using Pydantic AI?

Yes, use getitem to pull down core item data directly from the Wikibase REST API. Because of Pydantic AI's validation layer, you can trust that the structure of this retrieved data is exactly what your code expects.

Q: What safeguards does Pydantic AI provide when modifying Wikidata?

When using tools like createstatement or setitemdescription, the framework ensures type correctness. It validates that every piece of data you try to save adheres to your defined Python models, preventing runtime failures.

Ensure data correctness when querying Wikidata using Pydantic AI's type-safe MCP Server approach.

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 Pydantic AI

Create your Vinkius account to connect Wikidata to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute queries with `execute_sparql` via the MCP Server.

The `execute_sparql` tool runs SPARQL queries, and because you use Pydantic AI, every response is validated against your defined schema. If Wikidata returns unexpected data, your agent fails loudly with a validation error—no silent corruption. This forces correctness. You know the structure of the returned JSON before your agent processes it further.

Search for items using `search_items_vector`.

`search_items_vector` handles hybrid vector/keyword searches across Wikidata Items. Pydantic AI ensures that even when retrieving complex search results, the output conforms perfectly to your expected Python models. This level of strict type checking is crucial for building reliable agents where data integrity matters more than raw speed.

Update Item metadata with `set_item_description`.

`set_item_description` lets you write new text to an item's description, but Pydantic AI makes the process safe. It requires OAuth 2.0 Access Token authentication, and more importantly, it validates that the data payload matches your expected fields. This guarantees that even when updating knowledge records on Wikidata, you won’t accidentally send malformed JSON.

Setup guide

Set up Wikidata MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "wikidata-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Wikidata tools.",
)

result = await agent.run("List recent Wikidata transactions")
print(result.output)

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 Pydantic AI

The `execute_sparql` tool runs the query. Then, Pydantic AI intercepts the raw data and validates it against your defined models at runtime. If the result doesn't match, you get a clear validation error—you don't get garbage.

You have three main options: `search_items_vector` (for semantic item lookup), `search_properties_vector` (for metadata attributes), or running a precise SPARQL query via the MCP Server. They all feed into your type-safe workflow.

Yes, use `get_item` to pull down core item data directly from the Wikibase REST API. Because of Pydantic AI's validation layer, you can trust that the structure of this retrieved data is exactly what your code expects.

When using tools like `create_statement` or `set_item_description`, the framework ensures type correctness. It validates that every piece of data you try to save adheres to your defined Python models, preventing runtime failures.

The server handles structured text and metadata. Because Pydantic AI validates this at the boundary, you are guaranteed that the description string or statement payload is correctly formatted before it hits 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