How to Use the Together AI MCP in Vercel AI SDK

Q: Can I use Together AI with my existing OAuth authentication in Vercel AI SDK?

Yes. The setup supports an authProvider for OAuth, meaning you can secure your MCP calls using standard user sign-in flows built into the Vercel environment.

Real-time LLM results in Next.js and Svelte 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 Together AI MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Streaming Text Completions with the MCP Server

Use `text_completion` to get immediate text responses from Together AI models. Because this is an Edge Function compatible setup, your client sees the words appear on screen as they generate; there's no loading spinner. This real-time streaming capability lets you build polished user interfaces where the AI feels instant and responsive. You can use `chat_completion` for multi-message conversations that stream directly to React or Next.js.

Generating Images in Real Time

The `generate_image` tool lets your front end call Together AI instantly. Just provide a descriptive prompt, and the agent handles fetching the model ID and returning the resulting image data. You can combine this with streaming text calls to give users a complete, live experience—they submit a request, see text appear describing the generated asset, and then the image loads immediately after.

Managing Models and Fine-Tuning

Need to know what models are available? Call `list_available_models` to get the latest list of LLMs. For persistent features, use `create_finetune_job` with a base model ID and your training file ID. Checking job status is simple too; `list_finetune_jobs` shows you everything that's running on Together AI's infrastructure, keeping your whole application informed.

Setup guide

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

The SDK streams text and data directly to your frontend components (React, Next.js). Your user sees the result appear character by character as it's generated by the `text_completion` tool, making the experience feel native.

Yes. The setup supports an `authProvider` for OAuth, meaning you can secure your MCP calls using standard user sign-in flows built into the Vercel environment.

This setup primarily handles text inputs, model IDs, message arrays for chat completions, and image generation prompts. It's all about real-time data flow into the client UI.

The core benefit is that the tool results stream directly into your user interface. Instead of waiting for a single payload, data appears live—a huge upgrade over traditional loading spinners.

The MCP Server runs within an isolated sandbox environment. This means your agents can run complex tasks without interfering with other services or the host system.

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