How to Use the UpCloud MCP in Pydantic AI

Q: What if I need to check billing information with UpCloud using Pydantic AI?

The agent calls getbillingsummary. Because of runtime validation, you're guaranteed that the returned data structure for your monthly costs matches the expected format, preventing errors.

Q: Does UpCloud support resource modification with Pydantic AI?

Absolutely. Whether you use updatestorage to resize a disk or updateserver to change settings, the framework validates that your input parameters are typed correctly before sending the request.

Build reliable cloud workflows with Pydantic AI and the UpCloud MCP Server.

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 Pydantic AI

Create your Vinkius account to connect UpCloud to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Managing Virtual Machines

Need to change a server? You can start it up using `start_server`, or modify its config entirely via `update_server`. If you're done with it, `delete_server` handles the cleanup. It’s straightforward but needs accuracy. The power of Pydantic AI is that every response—say, from `get_server`—is validated against a strict schema. If UpCloud returns unexpected data fields, your agent fails loudly; no silent corruption.

Networking and Connectivity

Setting up connectivity requires precision. You can assign new IPs with `assign_ip`, or create a full private network using `create_network`. For redundancy, you might spin up multiple load balancers (`list_load_balancers`). Because the framework enforces types at runtime, you're guaranteed that when your agent uses tools like `update_network` or `create_router`, the parameters match exactly what the API expects.

Data Persistence and Backup

Never lose data. You can create a managed storage service using `create_object_storage`. If that fails, you have backups to fall back on with `restore_storage`. Also, use `list_storages` to check what's available. The type-safe nature means when the agent calls `create_database`, it knows exactly what data structure for parameters is needed—no guessing involved.

Setup guide

Set up UpCloud MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "upcloud-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to UpCloud tools.",
)

result = await agent.run("List recent UpCloud transactions")
print(result.output)

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 Pydantic AI

The MCP Server exposes its tools, and the Pydantic AI client validates every response against your defined Python models. This guarantees that when your agent acts on data from UpCloud, it's correct.

Yes. You can orchestrate a multi-step process: first list zones (`list_zones`), then create a new Kubernetes cluster (`create_kubernetes_cluster`), and finally get the credentials using `get_kubernetes_kubeconfig`.

The agent calls `get_billing_summary`. Because of runtime validation, you're guaranteed that the returned data structure for your monthly costs matches the expected format, preventing errors.

Absolutely. Whether you use `update_storage` to resize a disk or `update_server` to change settings, the framework validates that your input parameters are typed correctly before sending the request.

This server touches account audit logs and billing summaries. The type safety ensures that even when processing this sensitive account information, the agent only handles and validates expected fields.

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