Can my agent trigger a new deployment for a Coolify application?

Yes. Use the 'trigger_deployment' tool with the application UUID. The agent will initiate a full build pipeline, fetching the latest commit and rolling out the updated version directly on your server.

How do I retrieve the internal connection string for a managed database?

Provide the database UUID to the 'get_database' tool. Your agent will extrapolate the internal network URI (e.g., for PostgreSQL or MySQL), allowing you to securely link your apps without external port exposure.

Can I restart an application to apply new environment variables?

Absolutely. Use the 'restart_application' tool. The agent will execute an overlapping bounce, destroying old instances and initializing fresh replicas with the latest configuration and environment variables.

Coolify MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes

Name: Coolify
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 10 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Coolify through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

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

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Coolify Assistant",
            instructions=(
                "You help users interact with Coolify. "
                "You have access to 10 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Coolify"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Coolify MCP Server

Connect your Coolify instance to any AI agent and take full control of your self-hosting and private cloud workflows through natural conversation.

The OpenAI Agents SDK auto-discovers all 10 tools from Coolify through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Coolify, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

What you can do

Server Monitoring — List self-hosted nodes and retrieve intricate networking parameters including IP properties and Docker swarm statuses
Application Management — List all managed frontend/backend apps and fetch elaborate internal topology metrics like mapped GitHub branches and Traefik proxy paths
Lifecycle Control — Start, stop, and restart applications natively, allowing you to recycle container states and apply configuration updates instantly
Deployment Automation — Trigger raw build pipelines to fetch the latest commits, rebuild Nixpacks images, and roll out updated Docker versions
Database Oversight — Manage PostgreSQL, MySQL, and Redis configurations and extrapolate internal connection strings for secure application linking
Resource Navigation — asociating Project repositories to explicit application UUIDs required for downstream mutations and operational auditing

The Coolify MCP Server exposes 10 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Coolify to OpenAI Agents SDK via MCP

Follow these steps to integrate the Coolify MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 10 tools from Coolify

Why Use OpenAI Agents SDK with the Coolify MCP Server

OpenAI Agents SDK provides unique advantages when paired with Coolify through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Coolify + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Coolify MCP Server delivers measurable value.

Automated workflows: build agents that query Coolify, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries Coolify, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Coolify tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Coolify to resolve tickets, look up records, and update statuses without human intervention

Coolify MCP Tools for OpenAI Agents SDK (10)

These 10 tools become available when you connect Coolify to OpenAI Agents SDK via MCP:

get_application

Examines mapped GitHub branches, automatic rollout toggles (push to deploy), and assigned Traefik reverse proxy FQDN paths. Fetch elaborate internal topology metrics for a given Application

get_database

Highly required when linking newly provisioned Web Apps to Backend Datastores. Extrapolate internal configuration arrays for a Database

get_server

Verifies IP properties, SSH connection validation statuses, and Docker executing ports resolving across the cluster. Get configuration schema mapped to a specific Coolify Server Node

list_applications

Generates the crucial map associating Project repositories to explicit application UUIDs required for downstream mutations (like restarting and stopping). List all frontend/backend Applications actively managed by Coolify

list_databases

Isolates database bounding boxes mapping to applications so you can properly retrieve Connection Strings and backup cadence timelines. List managed PostgreSQL, MySQL, and Redis configurations

list_servers

Used to identify the raw physical endpoints running Docker swarms that host subsequent applications. List all self-hosted Server Nodes attached to Coolify

restart_application

Ensures updated config `.env` variables injected via Coolify take effect immediately in runtime RAM. Bounce a Coolify application recycling its container states

start_application

Spin up containers mapped to a suspended Application UUID

stop_application

Used precisely for pausing billing or restricting web perimeter ingress during a cyber incident directly via the Coolify dashboard API. Halt execution algorithms suspending the mapped Application

trigger_deployment

Performs `git fetch`, rebuilds Nixpacks images, caches dependencies, and rolls the updated Docker image out directly over the previous active application version. Trigger a raw build pipeline fetching the latest Git commit

Example Prompts for Coolify in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Coolify immediately.

"List all active servers in my Coolify instance"

"Trigger a deployment for application 'backend-api'"

"What is the connection string for database 'user-db-prod'?"

Troubleshooting Coolify MCP Server with OpenAI Agents SDK

Common issues when connecting Coolify to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Coolify + OpenAI Agents SDK FAQ

Common questions about integrating Coolify MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.