How to Use the Metorial MCP in OpenAI Agents SDK

Q: How do I monitor Metorial performance in OpenAI Agents SDK?

Use metorialgetusagemetrics to pull the cost and latency logs directly. This gives you a clear look at your serverless spend without any extra overhead.

Q: Can Metorial handle server lifecycle for OpenAI Agents SDK?

Yes, you can trigger metorialdeployserver and metorialdeleteserver directly from your code. It keeps your agent environment clean and your costs predictable.

Q: Does Metorial work with OpenAI Agents SDK for production traces?

Absolutely. You can use metoriallisttraces and metorialgettracedetails to audit every action your agents take in production.

Q: How do I list active nodes in my Metorial workspace?

Call metoriallistservers to get a full array of your currently provisioned MCP nodes. It's the fastest way to verify your infrastructure state.

Directly manage your serverless infrastructure and trace execution logs within the 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 Metorial MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Full lifecycle control for your agents

Deploy and dismantle your serverless infrastructure directly from your agent logic. You can use `metorial_deploy_server` to spin up your environment and `metorial_delete_server` to clear it out when the work is done. This keeps your resource footprint tight. You avoid paying for idle compute by managing your server states through the same client managing your agent behavior.

Deep visibility via OpenAI Agents SDK

Pull granular performance data to see exactly where your processes sit. `metorial_get_usage_metrics` provides the raw numbers on latency and cost, while `metorial_list_traces` lets you audit every transaction. Everything happens in real-time. You aren't guessing about bottlenecks because the data comes straight from your active serverless nodes.

Direct tool invocation for agents

Execute specific operations on your remote nodes without leaving your Python environment. `metorial_invoke_server_tool` handles the heavy lifting, sending your commands to the right container. It handles the routing so your agent stays focused on the task. You just define the payload and let the connection manage the delivery to your infrastructure.

Setup guide

Set up Metorial 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 Metorial tools at runtime.
3

Create your Agent

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

Run the agent

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

Use `metorial_get_usage_metrics` to pull the cost and latency logs directly. This gives you a clear look at your serverless spend without any extra overhead.

Yes, you can trigger `metorial_deploy_server` and `metorial_delete_server` directly from your code. It keeps your agent environment clean and your costs predictable.

Absolutely. You can use `metorial_list_traces` and `metorial_get_trace_details` to audit every action your agents take in production.

Call `metorial_list_servers` to get a full array of your currently provisioned MCP nodes. It's the fastest way to verify your infrastructure state.

We isolate your execution logs and usage metrics within a V8 sandbox. Only your authenticated endpoint token grants access to your specific serverless trace details.

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