How to Use the Databricks MCP in Vercel AI SDK

Build a real-time Databricks monitor in your UI using the Vercel AI SDK. No 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 Databricks MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Monitor Cluster Health Live

This server's tools let your agent feed a live dashboard with Databricks cluster status. Instead of polling an API and managing state, you just stream results from `list_clusters` to populate a table. Your agent can then use `get_cluster` to show details as a user clicks, all streaming directly into your UI components. This is perfect for building internal tools. Give your data science team a simple, live view of what compute is running without them ever leaving your app. You can also check on SQL warehouses with `list_warehouses` to monitor query engine availability.

Track Job Runs in Real Time

This MCP Server lets your agent track Databricks job status in real time. It calls `list_jobs` to get a list of all configured jobs, and then `list_job_runs` to stream the status of recent executions right into your application. You can build a custom notification system on top of this. When a job run fails, the data streams to your frontend and you can trigger a UI alert. It’s a direct line from your Databricks environment to your user's screen, powered by this MCP connection.

Explore Your Data Catalog with the Vercel AI SDK

Your agent can use tools like `list_catalogs` from this MCP server to let users browse your data landscape. From there, it can drill down with `list_schemas` to explore what's inside, right from your own application. Because the Vercel AI SDK streams tool results, the user experience is fast. They see catalogs and schemas appearing in the UI as the agent finds them. You can even get the current user's identity with `get_me` to tailor the view.

Setup guide

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

You get a single endpoint token from Vinkius for this Databricks server. In your code, use `createMCPClient` and pass the URL in the http transport. The SDK handles the connection and makes the tools available to `generateText`.

Yes, that's exactly what this is for. The AI SDK is built for streaming UI. You can have your agent call `list_clusters` or `list_job_runs` and the results will stream directly into your React or Svelte components for a live view.

Vinkius handles the Databricks authentication for you. Your Vercel AI SDK client only needs the single Vinkius endpoint URL and token. There's no need to manage Databricks keys or secrets in your frontend code.

Yes. The Vercel AI SDK and the MCP client are compatible with Vercel Edge Functions. You can run your agent on the edge to get low-latency responses for checking Databricks status from anywhere.

Your connection is secure. This MCP server only accesses metadata like cluster names, job run statuses, and catalog schemas. It never touches the actual data in your tables. All communication is over HTTPS and authenticated with your unique Vinkius token.

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