How to Use the Coolify MCP in Pydantic AI

Q: Does Pydantic AI support Coolify deployment triggers?

Yes, you can invoke triggerdeployment as a tool call. The agent waits for the response, ensuring the Git fetch and Nixpacks build process completes successfully.

Build type-safe infrastructure automation using Pydantic AI and the Coolify 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 Coolify MCP to Pydantic AI

Create your Vinkius account to connect Coolify 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 Coolify with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate infrastructure state in Pydantic AI

Every response from the server is checked against Pydantic models at runtime. If the API returns unexpected data, your agent fails immediately to prevent corrupted state. This ensures your infrastructure operations remain reliable. You never deal with hallucinated fields or silent errors during deployment.

Query server topology using Pydantic AI

Fetch elaborate metrics for any node with `get_server`. The agent verifies IP properties and Docker port resolution before moving to the next task in your pipeline. It confirms SSH connections are healthy before executing build commands. You get granular, typed data about your physical host environment.

Refresh app configs via Pydantic AI

Use `get_application` to examine specific branch mappings and Traefik reverse proxy paths. This confirms your routing setup matches your repository branch settings. Your agent can then trigger updates with full confidence in the configuration. It keeps your production environment strictly aligned with your code.

Setup guide

Set up Coolify 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": {
        "coolify-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

The framework validates incoming JSON against your defined Pydantic models. If the server output deviates from the expected schema, the agent raises a validation error instead of continuing with bad data.

You can register the MCP toolset for any external server instance. The framework treats each server as a source of validated tools for your agent.

Yes, you can invoke `trigger_deployment` as a tool call. The agent waits for the response, ensuring the Git fetch and Nixpacks build process completes successfully.

Every tool response is parsed into a Pydantic object. This gives you autocompletion and IDE support for all infrastructure data returned by your server nodes.

The connection uses encrypted transport protocols to move infrastructure schemas between your agent and the server. No raw database passwords or private API keys are ever stored in your agent's memory or logs.

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