How to Use the Groq MCP in Vercel AI SDK

Q: How do I configure Groq tools inside a Vercel AI SDK project?

Install @ai-sdk/mcp and initialize the client using createMCPClient. Pass the tools into streamText and remember to call mcpClient.close() once the generation finishes to avoid dangling connections.

Q: Can I stream llama-3.3-70b-versatile with Groq and Vercel AI SDK?

Yes, you can. You run createchatcompletion through the SDK's streaming functions to feed the Llama 3 model directly to your React components at LPU speeds.

Q: What is the correct way to clean up the client connection?

Always call mcpClient.close() after your generation runs complete. Leaving the connection open wastes resources and can block subsequent streaming sessions on serverless instances.

Get real-time Llama 3 text completions streaming directly into your React frontend using the Vercel AI SDK and Groq LPUs.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Groq MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Zero-latency UI rendering via Vercel AI SDK

When you build interactive web apps, waiting for API responses ruins the UX. Linking this MCP Server directly to your Edge Functions means your user gets instant text feedback. Calling `create_chat_completion` fires tokens back to the Vercel AI SDK stream before the user even finishes clicking. Standard setups make you wait for the whole model payload to load. By passing `list_available_models` to your frontend dropdown, you let users select LPU-powered architectures that render options in milliseconds.

Speed-focused code generation in React components

Developers building live coding sandboxes need immediate output. This setup pipes the `generate_code` tool output directly into your Next.js editor component without intermediate server lag. Your users watch raw code render line-by-line because the LPU executes the request instantly. If the user inputs broken syntax, your application can instantly trigger `explain_code` to show debugging tips right alongside the editor. The Vercel AI SDK handles the stream, making sure the explanation paints onto the screen without blocking the main browser thread.

Instant text polishing on the edge

Processing user-generated text usually requires heavy server-side processing. This MCP integration lets you run `fix_grammar` on text inputs directly from edge middleware, bypassing heavy backend servers. Your UI displays corrected text in real-time as the user types. For international audiences, combining this with `translate_text` allows instant localization on the fly. Because the Vercel AI SDK handles edge-compatible streams, your translation renders instantly, keeping your global users engaged.

Setup guide

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

Install `@ai-sdk/mcp` and initialize the client using `createMCPClient`. Pass the tools into `streamText` and remember to call `mcpClient.close()` once the generation finishes to avoid dangling connections.

Yes, you can. You run `create_chat_completion` through the SDK's streaming functions to feed the Llama 3 model directly to your React components at LPU speeds.

Absolutely, the lightweight HTTP transport fits perfectly inside Vercel's edge runtime limits. You get sub-second tool execution for tasks like `extract_entities` without hitting cold starts.

Always call `mcpClient.close()` after your generation runs complete. Leaving the connection open wastes resources and can block subsequent streaming sessions on serverless instances.

This MCP server processes your code blocks in memory and never stores them on Vinkius servers, ensuring complete transit isolation. The `explain_code` payload is destroyed immediately after execution.

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