How to Use the Fly.io MCP in Pydantic AI

Q: How does Pydantic AI validate Fly.io machine creation?

When your agent calls createmachine, Pydantic AI validates the returned microVM metadata against strict Python schemas. If the Fly.io API response contains unexpected fields, the framework raises a validation error before your code can proceed.

Q: Can I safely restart Fly.io instances using Pydantic AI?

Yes, you can use startmachine or stopmachine to control VM power states. Pydantic AI ensures that the machine identifiers passed to these tools match the expected string formats, preventing execution errors.

Q: How does Pydantic AI handle Fly.io volume metadata?

The framework parses the output of listvolumes into strongly-typed Python models. This guarantees that your agent reads accurate volume IDs and mount paths when managing stateful Fly.io applications.

Deploy and scale Fly.io edge infrastructure using this MCP Server with strict, runtime-validated Pydantic AI type safety.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fly.io MCP to Pydantic AI

Create your Vinkius account to connect Fly.io 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 Fly.io with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Edge Scaling with Pydantic AI

The `create_machine` tool spins up new Firecracker VMs with strict type validation enforced by Pydantic AI at runtime. If the Fly.io API returns an unexpected region format or an invalid machine ID, the framework catches it instantly. This prevents your agent from attempting to scale using malformed configuration payloads. You can safely execute `delete_machine` to prune idle instances, knowing the model cannot pass invalid identifiers to your production infrastructure.

Validated State Monitoring via MCP Server

The `get_machine` tool returns the exact operational status, image digest, and volume mapping of any active microVM. This MCP Server output is parsed against strict schemas, ensuring your agent never acts on corrupted or hallucinated state data. Should a machine transition to an unexpected state, the agent uses `start_machine` to force a reboot. The entire lifecycle is monitored using type-safe models, making your automated recovery loops highly predictable.

Strict Volume and App Discovery

The `list_volumes` tool retrieves all persistent NVMe storage drives attached to your application with complete structural validation. Your Pydantic AI agent verifies the disk sizes and mount paths before executing any infrastructure changes. This structured data is cross-referenced with app-wide networks using `get_app` and active namespaces from `list_apps`. You get zero-trust execution where every API response matches your Python type hints exactly.

Setup guide

Set up Fly.io 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": {
        "flyio-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Fly.io 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 Fly.io. 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 Fly.io 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 Fly.io MCP in Pydantic AI

When your agent calls `create_machine`, Pydantic AI validates the returned microVM metadata against strict Python schemas. If the Fly.io API response contains unexpected fields, the framework raises a validation error before your code can proceed.

Yes, you can use `start_machine` or `stop_machine` to control VM power states. Pydantic AI ensures that the machine identifiers passed to these tools match the expected string formats, preventing execution errors.

The framework parses the output of `list_volumes` into strongly-typed Python models. This guarantees that your agent reads accurate volume IDs and mount paths when managing stateful Fly.io applications.

No, Vinkius hosts and manages the MCP Server for you. You connect your external Pydantic AI agent to the managed HTTP endpoint using your single-token credentials.

Your Fly.io API tokens and configuration payloads are isolated within the V8 sandbox. Pydantic AI only receives the validated JSON schema outputs, ensuring your master account credentials are never exposed to the LLM or external networks.

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