Compatible with every major AI agent and IDE
What is the UpCloud MCP Server?
Connect your UpCloud account to any AI agent to manage your high-performance cloud infrastructure through natural language. From deploying servers to monitoring resource costs, take full control of your cloud environment.
What you can do
- Server Control — List, create, start, stop, and restart cloud servers across all global regions.
- Storage Management — List, create, modify, and clone storage resources to scale your data needs.
- Infrastructure Insights — Query available zones and physical hosts to optimize your deployment strategy.
- Account & Billing — Monitor your account limits, credits, and detailed monthly billing summaries.
- Pricing Transparency — Instantly list resource prices in your account's currency to manage cloud spend.
How it works
- Subscribe to this server
- Enter your UpCloud API credentials
- Start managing your cloud infrastructure from Claude, Cursor, or any MCP-compatible client
No more jumping between browser tabs to check server statuses or billing cycles. Your AI acts as a dedicated cloud architect and DevOps assistant.
Who is this for?
- DevOps Engineers — automate server lifecycle management and infrastructure audits without leaving the terminal or IDE.
- Cloud Architects — quickly query zone availability and host details to plan high-availability setups.
- Finance & Ops — retrieve billing summaries and resource prices to maintain budget control over cloud environments.
Built-in capabilities (46)
Assign a new IP address
Create a storage backup
Clone a storage
Create a new API token
Create a managed database instance
Create a firewall rule for a server
Create a Managed Kubernetes cluster
Create a managed load balancer
Create a new SDN private network
Create a Managed Object Storage service
Create a router
Create a new server
Create a new storage
Delete a server
Export account audit logs
Get UpCloud account information
Get monthly billing summary
Get host details
Get Kubernetes cluster credentials (kubeconfig)
Get detailed server information
Import data to storage
List API tokens
List account audit logs
List available database types and plans
List managed database services
List firewall rules for a server
List available hosts
List all IP addresses
List Managed Kubernetes (UKS) clusters
List managed load balancer services
List all SDN private networks
List Managed Object Storage services
List resource prices
List routers
List all servers
List all accessible storages
List available zones
Release an IP address
Restart a server
Restore storage from backup
Start a server
Stop a server
Modify PTR record or floating IP attachment
Modify network details
Modify server configuration
Modify or resize storage
Why OpenAI Agents SDK?
The OpenAI Agents SDK auto-discovers all 46 tools from UpCloud through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries UpCloud, another analyzes results, and a third generates reports, all orchestrated through Vinkius.
- —
Native MCP integration via
MCPServerSse, pass the URL and the SDK auto-discovers all tools with full type safety - —
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
- —
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
- —
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
UpCloud in OpenAI Agents SDK
UpCloud and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect UpCloud to OpenAI Agents SDK through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for UpCloud in OpenAI Agents SDK
The UpCloud MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 46 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in OpenAI Agents SDK only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
UpCloud for OpenAI Agents SDK
Every tool call from OpenAI Agents SDK to the UpCloud MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I check my current account balance and resource limits?
Yes! Use the get_account tool to retrieve your current credits and resource limits directly from your UpCloud account.
How do I see which global locations are available for deployment?
Simply ask the agent to run the list_zones action. It will provide a complete list of physical sites where you can deploy your infrastructure.
Is it possible to restart a server using its ID?
Yes. By providing the server's UUID to the restart_server tool, your AI agent can trigger a reboot of that specific instance immediately.
How does the OpenAI Agents SDK connect to MCP?
Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.
Can I use multiple MCP servers in one agent?
Yes. Pass a list of MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.
Does the SDK support streaming responses?
Yes. The SDK supports SSE and Streamable HTTP transports, both of which work natively with Vinkius.
MCPServerStreamableHttp not found
Ensure you have the latest version: pip install --upgrade openai-agents
Agent not calling tools
Make sure your prompt explicitly references the task the tools can help with.
Explore More MCP Servers
View all →
ROC AUC Evaluator
1 toolsCompute the exact Area Under the ROC Curve for binary classification predictions. Local, mathematically perfect, zero LLM estimation.

Google Books
8 toolsSearch and explore millions of books on Google Books — find titles, authors, reviews, previews and full text from any AI agent.

Checkout.com
10 toolsManage global payments via Checkout.com — process payments, capture funds, handle refunds, and vault instruments directly from any AI agent.

DeepSeek
12 toolsAccess powerful open-weight language models for reasoning, code generation, and complex problem solving at competitive cost.
