How to Use the AI21 Labs MCP in Vercel AI SDK

Q: How do I connect the AI21 Labs MCP Server to my Vercel AI SDK project?

Install @ai-sdk/mcp and call createMCPClient with the Vinkius HTTP URL. Pass the tools directly into streamText to get Jamba responses flowing to your React frontend. Always call the close method when the request finishes.

Q: How does Vercel AI SDK handle file management with the AI21 Labs tools?

You run ai21listfiles or ai21getfile directly inside your API routes. The Vercel AI SDK treats these operations as standard tool calls, returning metadata that you can map to your UI state.

Q: What is the fastest way to run grammar checks using these tools?

Pass ai21grammarcorrection to generateText inside your Next.js server action. The Vercel AI SDK executes the correction and returns the clean text to your client component in one round trip.

Stream Jamba-1.5 completions directly into your React frontends using Vercel AI SDK and this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AI21 Labs MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Jamba completions using this MCP Server.

The `ai21_chat_completion` tool feeds raw text generation directly into your Next.js edge functions. You hook this up to `streamText`, and the client renders words as they generate. No spinners, no waiting for the Jamba-1.5 payload. Your users see the output instantly because Vercel AI SDK handles the chunking. Writing custom socket code to stream Jamba text is no longer necessary. Just wire the HTTP transport and let the Jamba model fill the UI.

Ground AI answers with contextual data in Vercel AI SDK.

The `ai21_contextual_answers` tool forces the Jamba model to stick to your provided source files during a streaming session. You feed it the context, and your React components display verified facts instead of hallucinations. Passing this grounded tool to `generateText` keeps your Vercel AI SDK support bots honest. The SDK pipes the exact grounded answer back to the user interface, keeping the interaction tight and accurate.

Clean up user text live on the frontend.

The `ai21_grammar_correction` and `ai21_text_improvements` tools analyze draft posts or emails right inside your input fields. Your React frontend calls these tools as the user types, offering instant stylistic fixes. Instead of building heavy local parsing engines, you rely on these targeted AI21 Labs endpoints. The Vercel AI SDK updates the state, swaps the bad phrasing, and keeps your app's user experience fast.

Setup guide

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

Install `@ai-sdk/mcp` and call `createMCPClient` with the Vinkius HTTP URL. Pass the tools directly into `streamText` to get Jamba responses flowing to your React frontend. Always call the close method when the request finishes.

Yes, the lightweight HTTP transport works perfectly inside Edge runtimes. You invoke `ai21_contextual_answers` through Vercel AI SDK without bloating your bundle or hitting cold start delays.

You run `ai21_list_files` or `ai21_get_file` directly inside your API routes. The Vercel AI SDK treats these operations as standard tool calls, returning metadata that you can map to your UI state.

Pass `ai21_grammar_correction` to `generateText` inside your Next.js server action. The Vercel AI SDK executes the correction and returns the clean text to your client component in one round trip.

Your raw text inputs and file payloads processed by Vercel AI SDK go directly to our MCP sandbox before reaching the Jamba model endpoint. We never persist your drafts, chat history, or uploaded files on our servers.

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