How to Use the Atlan MCP in Vercel AI SDK

Q: How do I initialize the Atlan MCP Server in Vercel AI SDK?

Run npm install ai @ai-sdk/mcp first. Use createMCPClient with your Vinkius HTTP endpoint to expose Atlan tools like listusers to your Vercel AI SDK client.

Q: Can I stream Atlan asset details using Vercel AI SDK?

Yes, you use streamText to pipe the outputs of searchassets straight to your Vercel AI SDK frontend. The user watches the Atlan catalog schema load live.

Q: Do I need to close the connection after querying Atlan in Vercel AI SDK?

Always call mcpClient.close() at the end of your Vercel AI SDK execution loop. This prevents memory leaks in your Edge Functions when fetching Atlan classifications.

Get live Atlan metadata search results directly in your Next.js frontend with the Vercel 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 Atlan MCP to Vercel AI SDK

Create your Vinkius account to connect Atlan 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 Atlan with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Atlan search results via Vercel AI SDK

The `search_assets` tool lets your Vercel AI SDK application query your Atlan data catalog in real time. Your Next.js users see Atlan tables and schemas populating their browser instantly as the Vercel AI SDK retrieves the metadata. You configure this by passing the Atlan MCP client tools directly into your Vercel AI SDK streamText function. This setup bypasses slow API polling, rendering Atlan data assets in your Vercel frontend without annoying loading spinners.

Expose corporate glossaries in your web UI

The `list_glossaries` tool retrieves your company's business terms from Atlan directly into your edge-rendered Vercel AI SDK application. By feeding these Atlan terms to your Vercel AI SDK client, your frontend renders matching tooltips for complex data jargon on the fly. This integration relies on the createMCPClient method to establish a secure connection between Atlan and Vercel. You get immediate access to Atlan definitions in your Vercel AI SDK app without writing custom wrapper APIs.

Verify access controls live using this MCP Server

The `list_personas` tool fetches active Atlan governance roles so your Vercel AI SDK app can verify user context. Your Vercel agent checks who owns an Atlan dataset before displaying sensitive columns. Combine this with `list_purposes` to enforce Atlan data policies right at the Vercel edge. You protect your Atlan data catalog by running these Vercel AI SDK checks on every single prompt execution.

Setup guide

Set up Atlan 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 Atlan 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 Atlan 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 Atlan. 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 Atlan 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 Atlan MCP in Vercel AI SDK

Run `npm install ai @ai-sdk/mcp` first. Use `createMCPClient` with your Vinkius HTTP endpoint to expose Atlan tools like `list_users` to your Vercel AI SDK client.

Yes, you use `streamText` to pipe the outputs of `search_assets` straight to your Vercel AI SDK frontend. The user watches the Atlan catalog schema load live.

Vercel AI SDK passes your Vinkius token securely through the HTTP transport layer to authenticate with Atlan. You don't have to manage raw Atlan API keys in your Vercel frontend code.

Always call `mcpClient.close()` at the end of your Vercel AI SDK execution loop. This prevents memory leaks in your Edge Functions when fetching Atlan classifications.

Vercel AI SDK processes your Atlan database schemas and classification tags inside a secure V8 isolate. No raw Atlan credentials or metadata fields are stored outside your active Vercel session.

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