How to Use the Baseten MCP in Vercel AI SDK

Q: How do I run a Baseten prediction inside a Vercel AI SDK route?

Import the MCP client and register the predict tool inside your streamText function. Pass your input dictionary directly to the tool to invoke the serverless model.

Q: Can Vercel AI SDK check active Baseten deployments?

Yes, your agent calls listdeployments to inspect active inference setups. It reads the model status and returns the current active endpoints immediately.

Q: How does the Vercel AI SDK handle Baseten workspace secrets?

The SDK uses listsecrets to verify which environment variables exist in your workspace. It never exposes the raw values to the client-side code, keeping your keys safe.

Run serverless model inferences and stream the outputs directly to your React components using 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 Baseten MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run serverless predictions with Vercel AI SDK

The `predict` tool runs serverless model inference on Baseten using this MCP Server directly from your Edge Functions. It grabs your input tensors or dictionaries and feeds them straight to your active model deployment. Forget waiting on a slow backend to finish. The Vercel AI SDK streams these model outputs straight into your frontend UI, meaning your users see raw data render in real time without a single loading spinner blocking the screen.

Track active model deployments in real time

The `list_deployments` tool fetches the active inference instances currently running on your Baseten account. It gives you the exact state of your hardware and active endpoints. You can feed these live deployment metrics into your Next.js dashboard using the Vercel AI SDK. This lets you display active model statuses and scale events on a live admin page.

Generate dynamic UI controls from Baseten metadata

The `get_model` tool retrieves the exact configuration and setup details of a specific Baseten model. This tells your application exactly what parameters your model expects before you send a request. By coupling this with Vercel AI SDK, your frontend can automatically render matching input forms based on the model's expected tensor shapes. You stop hardcoding form fields and let the model metadata dictate the UI.

Setup guide

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

Import the MCP client and register the `predict` tool inside your `streamText` function. Pass your input dictionary directly to the tool to invoke the serverless model.

Yes, your agent calls `list_deployments` to inspect active inference setups. It reads the model status and returns the current active endpoints immediately.

The SDK uses `list_secrets` to verify which environment variables exist in your workspace. It never exposes the raw values to the client-side code, keeping your keys safe.

No. You run this MCP client directly inside your Next.js Edge Route. The tools execute server-side and stream the JSON results straight back to the browser.

Yes, your prediction inputs and Baseten model metadata never touch intermediate servers. The Vinkius MCP gateway runs inside a zero-trust V8 sandbox, routing your payload directly to Baseten and streaming the output straight to your Vercel deployment.

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