How to Use the data.world MCP in Vercel AI SDK

Q: How do I search the data.world catalog with the Vercel AI SDK?

Pass the searchcatalog tool to the generateText or streamText function. Your AI client will use it to run a full-text search against data.world. The results stream back, perfect for live-updating a search results component in your UI.

Q: Can I see my own datasets and projects?

Yes. The server includes listmydatasets and listmyprojects. Your agent can call these to get a summary of assets you own on data.world.

Stream data.world query results directly into your Vercel AI SDK app, character by character. No more loading spinners.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect data.world MCP to Vercel AI SDK

Create your Vinkius account to connect data.world 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 data.world with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Find and Display Datasets Live

Let users search your entire data.world catalog from your app's chat interface. The `search_catalog` tool hits the index and streams results back instantly. Your UI updates in real-time as the data arrives. Once they find a dataset, they can pull its full schema with `get_dataset_details`. Field definitions, file names, and license info will appear on screen as your agent processes them, thanks to the Vercel AI SDK's streaming capabilities.

Manage Projects in Your UI

Give users a direct window into their data.world projects. They can ask your agent to `list_my_projects` and see a summary appear. It's a faster way to check on status without leaving your application. Your users can dig deeper by fetching project specifics. Use `get_project_details` to show project members and objectives, or `list_project_insights` to display documented findings. All this data streams right into your React or Next.js components.

Connect Your MCP Server to data.world

This MCP Server connects your agent to the data.world API. Your app can now use tools to `list_my_datasets`, `list_my_collections`, and even check on `list_recent_activity`. Setup is just a few lines of code. You instantiate the client, pass it your Vinkius endpoint, and the tools are ready. The AI SDK handles the streaming, so you can focus on building the UI that displays the data.

Setup guide

Set up data.world 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 data.world 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 data.world 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 data.world. 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 data.world 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 data.world MCP in Vercel AI SDK

Pass the `search_catalog` tool to the `generateText` or `streamText` function. Your AI client will use it to run a full-text search against data.world. The results stream back, perfect for live-updating a search results component in your UI.

Yes. The server includes `list_my_datasets` and `list_my_projects`. Your agent can call these to get a summary of assets you own on data.world.

Vinkius manages the connection token. You just provide the secure MCP endpoint URL to the Vercel AI SDK's `createMCPClient` function. It handles the rest, so you don't need to manage API keys in your frontend code.

You get streaming tool results. Instead of waiting for a whole API call to finish, data from tools like `get_dataset_details` appears in your UI as it's received. This makes your app feel much faster and more responsive.

Yes. The server only has access to what the tools permit, like your profile metadata from `get_my_profile`. All communication happens over encrypted HTTPS through Vinkius's ephemeral sandboxes, and your authentication token is never exposed to the client-side code.

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