How to Use the UpCloud MCP in OpenAI Agents SDK

Q: Can the OpenAI Agents SDK handle multiple resource types?

Yep. You can manage databases via listdatabases and simultaneously configure a new Kubernetes cluster using createkubernetescluster. The agent handles these distinct operations in one workflow.

Q: What if I need to check my spending with UpCloud using the OpenAI Agents SDK?

You just call the getbillingsummary tool. The client retrieves your current monthly billing summary, giving you a direct view of costs without having to switch consoles.

Q: Does UpCloud support resource management with the OpenAI Agents SDK?

It does. You can scale up or down by calling updateserver or resizing storage using updatestorage. These modifications are executed safely within the agent's constrained environment.

Control your entire cloud stack with 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 UpCloud MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Servers and Networking

Need to spin up or tear down infrastructure? You can create a new server using `create_server` or stop it instantly with `stop_server`. Furthermore, you control network flow by calling `create_firewall_rule` or setting up private connections via `create_network`. Since this is built for production agents, the SDK validates every action. It handles complex handoffs between specialized tools so your agent doesn't just guess—it executes reliable infrastructure changes.

Handle Storage and Data Backup

Data integrity matters. Use `create_object_storage` to provision new buckets, or if things go sideways, restore lost data with `restore_storage`. You can also clone existing resources using `clone_storage`, which is great for testing before rolling out changes. The OpenAI Agents SDK adds built-in guardrails that validate the full sequence of calls. This means your agent won't accidentally lose data just because a single step failed.

Monitor and Manage Accounts

Keep tabs on what you’re spending. The `get_billing_summary` tool gives you the monthly rundown, while `list_audit_logs` lets you track who did what and when. You can also fetch basic account details with `get_account`. The full tracing available in this SDK means every single action—from listing IP addresses (`list_ips`) to creating a load balancer (`create_load_balancer`)—is logged for review.

Setup guide

Set up UpCloud 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 UpCloud tools at runtime.
3

Create your Agent

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

Run the agent

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

The UpCloud MCP Server exposes its 46 tools directly to your agent. Your AI client auto-discovers these capabilities, so you don't need to write any boilerplate code to connect them.

Yep. You can manage databases via `list_databases` and simultaneously configure a new Kubernetes cluster using `create_kubernetes_cluster`. The agent handles these distinct operations in one workflow.

You just call the `get_billing_summary` tool. The client retrieves your current monthly billing summary, giving you a direct view of costs without having to switch consoles.

It does. You can scale up or down by calling `update_server` or resizing storage using `update_storage`. These modifications are executed safely within the agent's constrained environment.

This server touches account audit logs and billing summaries. The guardrails in the OpenAI Agents SDK ensure that access to this sensitive account information requires proper validation.

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