How to Use the Coolify MCP in OpenAI Agents SDK

Manage your production infrastructure with the Coolify MCP Server directly through your OpenAI Agents SDK implementation.

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 OpenAI Agents SDK

Create your Vinkius account to connect Coolify to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate deployments in OpenAI Agents SDK

Trigger fresh builds for your apps without leaving your dev environment. The `trigger_deployment` tool fetches your latest Git commits and rebuilds Nixpacks images instantly. Your agent handles the rollout, replacing active versions with updated Docker images. It keeps your production state synced with your repo.

Inspect server health via OpenAI Agents SDK

Query your infrastructure nodes to see exactly what is running. The `list_servers` tool returns the physical endpoints hosting your Docker swarms. Use `get_server` to validate SSH connections and check specific port mappings. You get a clear picture of your cluster configuration without manual terminal access.

Control application states with OpenAI Agents SDK

Restart or stop services by targeting specific UUIDs. The `list_applications` tool maps your repositories to their unique identifiers, while `restart_application` pushes new `.env` variables into runtime RAM. If a security incident occurs, your agent can call `stop_application` to kill ingress immediately. It gives you precise control over your hosting perimeter.

Setup guide

Set up Coolify MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Coolify tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Coolify tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Coolify tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Coolify Agent",
            instructions="You have access to Coolify tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the required SDK and configure the HTTP stream parameters to point at your hosted endpoint. Pass the server instance into your agent constructor to enable automatic tool discovery.

Yes, every tool execution runs through your defined safety constraints. The agent validates actions before they hit your infrastructure, ensuring your build pipelines stay predictable.

You can list and inspect your database configurations using the provided toolset. This allows your agent to retrieve connection strings and track backup timelines for PostgreSQL, MySQL, or Redis.

The server triggers a container recycle to apply the latest configuration changes. It ensures that any updated environment variables take effect in your live runtime environment.

The server only touches your infrastructure metadata like IP addresses, FQDN paths, and container UUIDs. Your actual database content remains strictly within your private storage volumes, protected by your own access credentials.

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