How to Use the Baseten MCP in OpenAI Agents SDK

Q: How do I connect the Baseten MCP to the OpenAI Agents SDK?

Install the package with pip install openai-agents. Create an MCPServerStreamableHttp object with your endpoint URL and pass it directly to your Agent constructor.

Q: Can the OpenAI Agents SDK run Baseten model predictions?

Yes, it executes serverless inference using the predict tool. Built-in guardrails force the agent to format the tensor shapes correctly before making the call.

Q: Does this MCP Server expose my Baseten secrets?

No, the listsecrets tool only returns the names of securely managed workspace secrets. The actual secret values remain completely hidden from the agent.

Connect Baseten to the OpenAI Agents SDK to manage model deployments and run serverless inference inside your production systems.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Baseten MCP to OpenAI Agents SDK

Create your Vinkius account to connect Baseten 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 Baseten with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trigger Serverless Inference via MCP Server

The `predict` tool lets your agent fire strict tensor shapes or dictionaries straight at your Baseten instances. OpenAI guardrails validate the payload structures before execution. That stops malformed requests dead in their tracks before they hit your production endpoints. You get full tracing on every single inference call right in your dashboard. Handoffs between specialized agent nodes happen automatically the second a model prediction returns the required output.

Monitor Active Deployments

The `get_deployment` and `list_deployments` tools pull explicit details about your running inference bounds. Your OpenAI agent checks these stats to route traffic or verify that a specific model version is actually live before attempting to use it. Zero configuration is required to expose these commands. Setup means just passing the HTTP streamable URL to your agent constructor, and it auto-discovers the routing options immediately.

Audit Workspace Configurations

Tools like `list_secrets`, `get_model`, and `list_models` give your system read-only visibility into your Baseten environment. The agent verifies which workspace secrets exist without ever seeing their actual values. This strict separation maintains security while allowing automated health checks. Your production setup stays clean because the agent operates entirely within the boundaries you define.

Setup guide

Set up Baseten 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 Baseten tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Baseten 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="Baseten Agent",
            instructions="You have access to Baseten 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 Baseten. 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 Baseten 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 Baseten MCP in OpenAI Agents SDK

Install the package with `pip install openai-agents`. Create an `MCPServerStreamableHttp` object with your endpoint URL and pass it directly to your Agent constructor.

Yes, it executes serverless inference using the `predict` tool. Built-in guardrails force the agent to format the tensor shapes correctly before making the call.

No, the `list_secrets` tool only returns the names of securely managed workspace secrets. The actual secret values remain completely hidden from the agent.

Every tool invocation routes through the standard OpenAI tracing dashboard. You see exactly when the agent calls `get_deployment` or `list_models`.

Your workspace secrets, tensor shapes, and model configurations never leak into public training data. Vinkius runs the connection inside a zero-trust V8 Isolate Sandbox, guaranteeing ephemeral execution and strict isolation for your proprietary inference payloads.

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