How to Use the Wikidata MCP in Vercel AI SDK

Q: Can I use the ai-sdk to check Wikidata item relationships?

Yes, you can retrieve statements for any given Item using getitemstatements. The streaming nature means that if an item has hundreds of facts, they appear sequentially in your application.

Q: What is the best way to search Wikidata with the ai-sdk?

For general discovery, use a hybrid search via searchitemsvector. The results are formatted for streaming display, so you can show users what they're looking up as the data comes in.

See structured Wikidata data stream live and instantly within your application using the ai-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 Vercel AI SDK

Create your Vinkius account to connect Wikidata to Vercel AI 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Search Wikidata Concepts using the MCP Server

You can run a hybrid search for concepts or properties using `search_items_vector` and `search_properties_vector`. The results stream right into your React component, letting the user see matches appear instantly. This is perfect when building UIs that need to feel live.

Execute Structured Wikidata Queries with ai-sdk

Need specific facts? Use `execute_sparql` to run complex queries against the graph. The returned data streams through the SDK, feeding your application's state management without a loading spinner delay. This gives you fine-grained control over when data updates.

Update Wikidata Records using the ai-sdk

When your agent confirms new data, use `create_statement` or `set_item_description`. Because this is tied to streaming, you get confirmation that a record was updated in real time. You can show immediate feedback to the user, making the interaction feel snappy.

Setup guide

Set up Wikidata MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Wikidata tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Wikidata transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

The SDK streams results directly into your UI as they arrive. Instead of waiting for a massive JSON payload, you process chunks of data immediately, making it feel faster for the end user.

Yes, you can retrieve statements for any given Item using `get_item_statements`. The streaming nature means that if an item has hundreds of facts, they appear sequentially in your application.

For general discovery, use a hybrid search via `search_items_vector`. The results are formatted for streaming display, so you can show users what they're looking up as the data comes in.

Use it anytime your user experience depends on real-time feedback. If displaying retrieved knowledge from Wikidata feels slow, streaming it through this MCP Server will fix that feeling.

The primary data type is structured triples (subject, predicate, object), which you manipulate using `create_statement` and `set_item_description`.

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