How to Use the AI21 Studio MCP in Vercel AI SDK

Q: Can Vercel AI SDK stream AI21 Studio Jamba model outputs?

Yes. The chatcompletion tool returns data in chunks that the SDK pipes straight to your React frontend. Your users see the text appear instantly.

Stream AI21 Studio Jamba models and text tools directly into your React or Next.js UI using 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 AI21 Studio MCP to Vercel AI SDK

Create your Vinkius account to connect AI21 Studio 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 AI21 Studio with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Text Generation with Vercel AI SDK

Pushing raw Jamba output to the frontend used to require custom middleware. Now you pass the `chat_completion` tool straight into your Next.js route. Users watch the tokens print live on screen instead of staring at a loading state. You get full access to the Jamba 1.5 family right at the edge. If your users need long-form generation, call `text_completion` and let the Vercel transport handle the chunking.

Real-time Grammar and Paraphrasing

Building an AI21-powered writing assistant means giving users instant feedback. Hook up the `grammar_corrections` tool to a text area component. As they type, the MCP server runs the text through the engine and streams the fixes back. You can also wire up the `paraphrase` tool for tone adjustments. Give your end users a dropdown for casual or formal styles. The response updates the UI state immediately.

Instant Document Summaries via MCP

Summarizing large text dumps with AI21 breaks user experiences if they block the main thread. Send those massive blocks to the `summarize` tool. Vercel AI SDK keeps the connection open while the model processes the chunk. For search features, use `embed_texts` to generate vector representations on the fly. The V8 isolate sandbox ensures your API keys never leak to the client bundle.

Setup guide

Set up AI21 Studio 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 AI21 Studio 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 AI21 Studio 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 AI21 Studio. 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 AI21 Studio 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 AI21 Studio MCP in Vercel AI SDK

Install @ai-sdk/mcp in your project. Initialize the client with createMCPClient pointing to your Vinkius URL. Pass the tools directly to the streamText function.

Yes. The chat_completion tool returns data in chunks that the SDK pipes straight to your React frontend. Your users see the text appear instantly.

It works perfectly on the edge. Vinkius handles the underlying infrastructure. Just remember to call mcpClient.close() when your route finishes.

You get a full suite of language utilities. Call paraphrase, grammar_corrections, or segmentation right from your server actions.

Your raw text prompts and document chunks run through an ephemeral V8 isolate sandbox. Vinkius destroys the environment immediately after the API call completes. Zero trust means nothing gets stored.

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