How to Use the Gridscale (IaaS & PaaS Cloud Hosting API) MCP in Pydantic AI

Q: Can my Pydantic AI agent safely shut down servers using this Gridscale (IaaS & PaaS Cloud Hosting API) MCP server?

Yes. Your agent can run shutdownserver to initiate an ACPI shutdown, or use setserverpower to control the power state directly. Every response from these tools is validated to confirm the power state change succeeded.

Q: How do I list and verify templates before provisioning?

Your agent can call listtemplates to get a validated list of available OS images. Because the output is cast to a strict Pydantic model, your agent can reliably select the correct template UUID to pass into createserver.

Q: How is my Gridscale infrastructure data protected when using this tool?

All resource payloads, such as server IDs from listservers or network configurations from listnetworks, are processed within Vinkius's secure, ephemeral V8 sandboxes. Your raw infrastructure data is never stored, maintaining strict isolation between your cloud environment and the LLM.

Control your Gridscale cloud infrastructure with absolute type safety using Pydantic AI and MCP.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Gridscale (IaaS & PaaS Cloud Hosting API) MCP to Pydantic AI

Create your Vinkius account to connect Gridscale (IaaS & PaaS Cloud Hosting API) 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 Gridscale (IaaS & PaaS Cloud Hosting API) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate server configurations with Pydantic AI

When managing infrastructure, a single bad parameter can break your deployment. Pydantic AI ensures that every argument sent to `create_server` matches your strict schema before the API call is made. If the agent tries to pass an invalid server name or an unsupported location, the framework catches the error at runtime. The same validation applies to responses. When the agent queries `list_servers`, the returned data is parsed into Pydantic models. This prevents your agent from working with malformed payloads or hallucinated fields.

Type-safe network and storage attachments via MCP

Linking resources requires precise IDs and states. Your agent can fetch available IPs using `list_ips` and link them safely using `link_ip_to_server`. Because Pydantic AI enforces type boundaries, you can be sure that the IP and server IDs match the expected formats before execution. When attaching disk volumes with `link_storage_to_server`, the agent can first check if the server is offline by calling `get_server_power`. This strict, type-safe coordination prevents API errors and keeps your storage volumes from entering corrupted states.

Type-validated infrastructure monitoring

Telemetry data must be accurate if you are using it to trigger scaling actions. By fetching metrics with `get_server_metrics`, your agent gets structured data that is immediately validated against your internal Pydantic schemas. This ensures your scaling logic never triggers off of corrupted or incomplete metric payloads. The agent can also audit your account's network layout using `list_networks` and `list_firewalls`. By validating these configurations, you can build automated security scanners that reliably detect open ports or unmapped subnets.

Setup guide

Set up Gridscale (IaaS & PaaS Cloud Hosting API) 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": {
        "gridscale-iaas-paas-cloud-hosting-api-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Gridscale (IaaS & PaaS Cloud Hosting API) tools.",
)

result = await agent.run("List recent Gridscale (IaaS & PaaS Cloud Hosting API) 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 Gridscale. 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 Gridscale (IaaS & PaaS Cloud Hosting API) 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 Gridscale (IaaS & PaaS Cloud Hosting API) MCP in Pydantic AI

Initialize the MCPToolset using your Vinkius HTTP endpoint. Pass the toolset object directly into the toolsets parameter of your Pydantic AI Agent to expose all seventeen cloud management tools with automatic runtime validation.

The framework will raise a validation error instantly. Instead of letting your agent make decisions based on corrupted data, the execution halts loudly, allowing you to catch API drift or schema mismatches immediately.

Yes. Your agent can run `shutdown_server` to initiate an ACPI shutdown, or use `set_server_power` to control the power state directly. Every response from these tools is validated to confirm the power state change succeeded.

Your agent can call `list_templates` to get a validated list of available OS images. Because the output is cast to a strict Pydantic model, your agent can reliably select the correct template UUID to pass into `create_server`.

All resource payloads, such as server IDs from `list_servers` or network configurations from `list_networks`, are processed within Vinkius's secure, ephemeral V8 sandboxes. Your raw infrastructure data is never stored, maintaining strict isolation between your cloud environment and the LLM.

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