How to Use the CoreWeave (AI GPU Cloud) MCP in OpenAI Agents SDK

Q: How do agent handoffs work when managing CoreWeave (AI GPU Cloud) via OpenAI Agents SDK?

You define one agent for VPC management with createvpc and another for model serving with createdeployment. The SDK handles the transition between them when the system detects a shift in the user request, using the MCP standard to map tools to agent capabilities.

Spin up CoreWeave GPU clusters and manage VPCs directly within your OpenAI Agents SDK production workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CoreWeave (AI GPU Cloud) MCP to OpenAI Agents SDK

Create your Vinkius account to connect CoreWeave (AI GPU Cloud) 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 CoreWeave (AI GPU Cloud) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Guardrails on CoreWeave MCP Server Deployments

This MCP Server exposes `create_deployment` and `update_deployment` tools directly to your Python codebase. When your OpenAI agent decides to scale up an inference gateway, the SDK validates the action against your guardrails before hitting the CoreWeave API. You get complete safety because bad parameters trigger instant blocks. Your system avoids accidental over-provisioning or misconfigured gateways without you writing manual checks.

Hand Off CoreWeave Cluster Provisioning to Specialists

The `create_cluster` and `get_cluster` tools let you build a dedicated infrastructure agent using this MCP toolset. When a main agent needs a new Kubernetes environment, it hands the task to this specialist. The specialist handles the setup, verifies the CKS cluster details, and reports back. This keeps your primary logic clean while isolating complex infrastructure tasks.

Trace Live GPU Metrics in Your OpenAI Dashboard

Your agents fetch active telemetries using `query_metrics` and `query_logs` to diagnose performance issues. The OpenAI dashboard traces these tool calls step-by-step so you see exactly what raw data the agent used to make scaling decisions. No more guessing why an agent updated an inference capacity claim. Every Prometheus metric query and Loki log search is logged in your standard OpenAI execution trace.

Setup guide

Set up CoreWeave (AI GPU Cloud) 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 CoreWeave (AI GPU Cloud) tools at runtime.
3

Create your Agent

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

Run the agent

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

You configure your CoreWeave credentials once on the Vinkius platform. The OpenAI Agents SDK talks to our secure endpoint, meaning your production environment doesn't expose raw infrastructure keys to the agent runtime.

Yes, you control this at the agent definition level. If you only want an agent to read cluster status, expose only `list_clusters` and `get_cluster`, preventing any accidental writes.

You define one agent for VPC management with `create_vpc` and another for model serving with `create_deployment`. The SDK handles the transition between them when the system detects a shift in the user request, using the MCP standard to map tools to agent capabilities.

Caching prevents the SDK from repeatedly querying the 24 tools available on the server. It speeds up agent initialization times and reduces latency on every chat turn.

Vinkius runs the server inside an isolated sandbox, keeping your API tokens and raw telemetry logs private. Only the final tool output reaches your OpenAI agent, maintaining a strict boundary around your GPU cloud setup.

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