How to Use the Together AI MCP in OpenAI Agents SDK

Q: What if I need to generate images with Together AI and my agents using OpenAI Agents SDK?

You can use the generateimage tool right from your agent's workflow. You just pass a model ID and a descriptive prompt, andTogether AI returns an image for your application to display.

Q: Can Together AI handle multiple models when running agents with OpenAI Agents SDK?

Absolutely. The listavailablemodels tool lets your agent check every model on Together AI before deciding which one is best suited for the job. It's all managed through the MCP Server.

Build Production Agents for OpenAI Agents 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 OpenAI Agents SDK

Create your Vinkius account to connect Together AI to OpenAI Agents 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Chat Completions

Your agent hits the chat completion tool when it needs conversation. You just pass a model ID and an array of messages, and Together AI handles the rest. This lets your deployed product maintain context across multiple turns. It's perfect for building conversational flows that actually work in production.

Generate Embeddings

Need to search a database of text? Your agent calls `generate_embeddings`. You give it the model ID and an array of strings, and Together AI spits out vector embeddings. This capability is how your system powers semantic searches. It's essential for giving your agent access to private knowledge bases.

Create Fine-Tuning Jobs

When the base model isn't enough, your team needs custom training. The `create_finetune_job` tool lets your agent initiate a job by providing a base model ID and a specific training file ID. It sets up dedicated models optimized for your domain language. This means your agents don't just talk; they sound like people who actually work in this industry.

Setup guide

Set up Together AI MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Together AI tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Together AI tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Together AI tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Together AI Agent",
            instructions="You have access to Together AI tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

The OpenAI Agents SDK automatically discovers the MCP tools from Together AI. Crucially, it includes built-in guardrails that check agent actions before they run. This keeps your production system safe.

You can use the `generate_image` tool right from your agent's workflow. You just pass a model ID and a descriptive prompt, andTogether AI returns an image for your application to display.

Absolutely. The `list_available_models` tool lets your agent check every model on Together AI before deciding which one is best suited for the job. It's all managed through the MCP Server.

This server handles text prompts, model IDs, training file IDs, and descriptive image prompts. All inputs are treated as operational context by your agent.

The auto-discovery feature in the OpenAI Agents SDK handles compatibility checks for you. You just pass the server endpoint, and your agent figures out all available tools.

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