How to Use the Coolify MCP in CrewAI

Q: How do multiple CrewAI agents coordinate during a Coolify deployment?

One agent can trigger the build using triggerdeployment, while another agent monitors the application state via getapplication. They share status updates through CrewAI's shared memory.

Q: Can a CrewAI agent autonomously restart a failing Coolify container?

Yes, you can authorize an agent to call restartapplication if it detects that container states are unhealthy. This allows for autonomous self-healing of your self-hosted services.

Q: How does CrewAI handle database backups on Coolify?

The crew uses listdatabases to check backup cadence timelines. If an agent detects a missed backup window, it can flag the issue for human review or trigger an alert.

Deploy a team of specialized CrewAI agents to autonomously manage, monitor, and scale your Coolify cluster with this 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 CrewAI

Create your Vinkius account to connect Coolify to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Infrastructure Monitoring

This MCP Server exposes `list_servers` to let your operations crew run continuous health checks across your self-hosted servers. A monitor agent calls `list_servers` to check host endpoints, while a triage agent uses `get_server` to check SSH connection statuses. If a Docker port fails to resolve, the crew collaborates to diagnose the issue. The agents share context through their memory layer, allowing them to pinpoint whether the host machine or the container runtime is failing.

Autonomous Incident Escalation with CrewAI

When an application crashes, a specialized recovery agent uses `restart_application` to recycle container states and inject updated `.env` variables. If the container fails to start, the agent escalates the issue to a senior moderator agent. The moderator agent can then call `stop_application` to prevent further traffic from hitting the broken endpoint. This automated coordination ensures your self-hosted services remain stable without requiring 24/7 human on-call shifts.

Coordinated Database Provisioning

Your database agent uses `list_databases` via the MCP Server to isolate existing PostgreSQL or Redis bounding boxes and get connection strings. Meanwhile, a frontend agent maps these parameters to newly provisioned web apps. By calling `get_database`, the crew checks that the database config arrays match your application's requirements. This coordinated approach eliminates manual environment variable configuration errors during deployment.

Setup guide

Set up Coolify MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Coolify tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Coolify Analyst",
    goal="Access and analyze Coolify data via MCP.",
    backstory="Expert analyst with direct Coolify access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Coolify transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Coolify Analyst",
        goal="Access and analyze Coolify data via MCP.",
        backstory="Expert analyst with direct Coolify access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Coolify transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

One agent can trigger the build using `trigger_deployment`, while another agent monitors the application state via `get_application`. They share status updates through CrewAI's shared memory.

Yes, you can authorize an agent to call `restart_application` if it detects that container states are unhealthy. This allows for autonomous self-healing of your self-hosted services.

The crew uses `list_databases` to check backup cadence timelines. If an agent detects a missed backup window, it can flag the issue for human review or trigger an alert.

You can pass the Vinkius endpoint URL directly into your CrewAI Agent definition using the `mcps` parameter. This exposes all Coolify management tools to your crew instantly.

All retrieved connection strings, database bounding boxes, and GitHub repository maps are processed in memory within the secure V8 isolate sandbox. No sensitive database credentials or server configurations are cached or stored on external servers.

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