Coolify MCP
Enables AI assistants to interact with Coolify self-hosted instances for application deployment, management, and monitoring. Features 4 unified tools optimized for VS Code's limits, covering app management, environment configuration, system administr
What is Coolify MCP?
Coolify MCP is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to enables ai assistants to interact with coolify self-hosted instances for application deployment, management, and monitoring. features 4 unified tools optimized for vs code's limits, covering app manag...
Enables AI assistants to interact with Coolify self-hosted instances for application deployment, management, and monitoring. Features 4 unified tools optimized for VS Code's limits, covering app management, environment configuration, system administr
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- list_servers
- get_server
- list_services
- create_service
- delete_service
Use Cases
Maintainer
Works with
Installation
NPM
npx -y @masonator/coolify-mcpManual Installation
npx -y @masonator/coolify-mcpConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Coolify MCP
The Coolify MCP Server bridges AI assistants with your self-hosted Coolify instance, giving you natural-language control over application deployments, environment configuration, server health, and infrastructure management. It exposes 42 tools covering everything from listing projects and servers to deploying apps, updating environment variables in bulk, and searching Coolify's documentation — all without leaving your AI chat interface.
Prerequisites
- Node.js 18 or higher
- A running Coolify instance version 4.0.0-beta.460 or later
- A Coolify API access token (generated in Coolify under Settings > API)
- An MCP-compatible client such as Claude Desktop, Claude Code, or Cursor
Generate a Coolify API token
Log in to your Coolify instance, navigate to Settings > API, and create a new personal access token. Copy the token value — you will not be able to see it again.
Note your Coolify base URL
This is the URL you use to access your Coolify dashboard, e.g. https://coolify.example.com. If running locally it defaults to http://localhost:3000.
Add the server to Claude Desktop
Open ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) and add the coolify entry with your token and base URL.
Or add via Claude Code CLI
Use the claude mcp add command for a quick one-liner setup.
claude mcp add coolify \
-e COOLIFY_BASE_URL="https://your-coolify-instance.com" \
-e COOLIFY_ACCESS_TOKEN="your-api-token" \
-- npx @masonator/coolify-mcp@latestRestart your MCP client and verify the connection
Restart Claude Desktop or reload your MCP client. Ask it for an overview of your Coolify infrastructure to confirm the server is responding correctly.
Coolify MCP Examples
Client configuration
Complete claude_desktop_config.json entry for the Coolify MCP Server.
{
"mcpServers": {
"coolify": {
"command": "npx",
"args": ["-y", "@masonator/coolify-mcp"],
"env": {
"COOLIFY_ACCESS_TOKEN": "your-api-token-here",
"COOLIFY_BASE_URL": "https://your-coolify-instance.com"
}
}
}
}Prompts to try
Sample prompts once the Coolify MCP Server is connected.
- "Give me an overview of my Coolify infrastructure"
- "List all applications and their current status"
- "Diagnose the api-backend application and tell me if there are any issues"
- "Update the DATABASE_URL environment variable for the production app"
- "Restart all apps in the production project"
- "Search the Coolify docs for health check configuration"Troubleshooting Coolify MCP
Authentication errors or 401 responses when calling tools
Double-check your COOLIFY_ACCESS_TOKEN value. Token secrets are only shown once in the Coolify UI — if you lost it, delete the old token and generate a new one under Settings > API.
COOLIFY_BASE_URL connection refused or timeout
Ensure the Coolify instance is running and reachable from the machine running the MCP server. If Coolify is behind a VPN or firewall, the MCP server process must also have access. For local instances verify the port (default 3000) is correct.
Server requires Coolify version 4.0.0-beta.460 or later
Check your Coolify version in the dashboard. If it is older, update Coolify through its built-in update mechanism before using this MCP server.
Frequently Asked Questions about Coolify MCP
What is Coolify MCP?
Coolify MCP is a Model Context Protocol (MCP) server that enables ai assistants to interact with coolify self-hosted instances for application deployment, management, and monitoring. features 4 unified tools optimized for vs code's limits, covering app management, environment configuration, system administr It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Coolify MCP?
Install via npm with the command: npx -y @masonator/coolify-mcp. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
Which AI clients work with Coolify MCP?
Coolify MCP works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Coolify MCP free to use?
Yes, Coolify MCP is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Coolify MCP Alternatives — Similar Cloud Services Servers
Looking for alternatives to Coolify MCP? Here are other popular cloud services servers you can use with Claude, Cursor, and VS Code.
Open WebUI
★ 138.2kUser-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Anything LLM
★ 60.4kThe all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.
LocalAI
★ 46.4kLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
Nacos
★ 33.0kan easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.
Xiaozhi ESP32
★ 26.7k本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.
Gateway
★ 11.8kA blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.
Browse More Cloud Services MCP Servers
Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Coolify MCP in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Coolify MCP?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.