Enhanced Coolify MCP Server
A powerful Model Context Protocol server that enables AI assistants to manage Coolify infrastructure through natural language, supporting application deployment, database management, resource monitoring, and DevOps automation.
README
🚀 Enhanced Coolify MCP Server
A powerful, enhanced Model Context Protocol (MCP) server for Coolify that enables AI assistants to manage your entire Coolify infrastructure through natural language. Deploy applications, manage databases, monitor services, and automate your DevOps workflows - all through simple conversations with AI.
✨ What Makes This Enhanced?
This is a significantly enhanced version of the original Coolify MCP Server with 15+ new tools and powerful automation capabilities:
🎯 New Capabilities
- Complete Application Lifecycle Management - Create, deploy, monitor, and manage applications
- Infrastructure Automation - One-click deployment of PostgreSQL, Redis, and MinIO stacks
- Real-time Monitoring - Resource usage, logs, and deployment status tracking
- Environment Management - Bulk environment variable updates and configuration
- Docker Compose Support - Deploy custom Docker Compose services
- Advanced Deployment Control - Monitor, cancel, and manage deployments
🛠️ Perfect For
- Developers - Streamline your deployment workflows
- DevOps Teams - Automate infrastructure management
- Beginners - Easy setup with clear examples
- AI Enthusiasts - Natural language infrastructure control
📋 Prerequisites
Before installation, ensure you have:
- Node.js 18+ installed
- Git installed
- Access to a Coolify server (self-hosted, v0cl.one, or Coolify Cloud)
- Coolify API token with appropriate permissions
🎬 Quick Start Guide
Option A: Interactive Setup (Recommended for Beginners)
# Clone and run the interactive setup guide
git clone https://github.com/dazeb/coolify-mcp-enhanced.git
cd coolify-mcp-enhanced
npm install && npm run build
node setup-guide.js
The interactive guide will walk you through:
- ✅ Getting your Coolify API token
- ✅ Configuring your server URL
- ✅ Setting up your AI assistant
- ✅ Testing the connection
Option B: Manual Setup
Step 1: Get Your Coolify API Token
- Log into your Coolify dashboard (e.g.,
https://your-coolify-server.com) - Go to API Tokens (usually in Settings or Profile)
- Create a new token with appropriate permissions
- Copy the token - it looks like:
0|1234567890abcdef...
Step 2: Install the Enhanced MCP Server
# Clone the repository
git clone https://github.com/dazeb/coolify-mcp-enhanced.git
cd coolify-mcp-enhanced
# Install dependencies and build
npm install
npm run build
Step 3: Configure Your Environment
# Set your Coolify server details
export COOLIFY_ACCESS_TOKEN="0|your-actual-token-here"
export COOLIFY_BASE_URL="https://your-coolify-server.com"
# Example for common Coolify hosting services:
# export COOLIFY_BASE_URL="https://s1.v0cl.one" # v0cl.one hosting
# export COOLIFY_BASE_URL="https://app.coolify.io" # Coolify Cloud
# export COOLIFY_BASE_URL="https://coolify.yourdomain.com" # Self-hosted
Step 4: Test the Connection
# Test basic functionality
node test-mcpaas.js
# You should see:
# ✅ GitHub Repo: PASS
# ✅ Basic connectivity working
Step 5: Quick Verification
# Test MCP server directly
echo '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"list_servers","arguments":{}}}' | node dist/index.js
# Expected output: JSON response with your Coolify server information
⚡ One-Command Installation
For AI agents or advanced users, here's the complete installation in one command:
git clone https://github.com/dazeb/coolify-mcp-enhanced.git && cd coolify-mcp-enhanced && npm install && npm run build && echo "✅ Installation complete! Run 'node setup-guide.js' for configuration."
🤖 AI Assistant Integration
Claude Desktop Setup
Add this to your claude_desktop_config.json:
{
"mcpServers": {
"coolify-enhanced": {
"command": "node",
"args": ["/full/path/to/coolify-mcp-enhanced/dist/index.js"],
"env": {
"COOLIFY_ACCESS_TOKEN": "0|your-actual-token-here",
"COOLIFY_BASE_URL": "https://your-coolify-server.com"
}
}
}
}
Kiro IDE Setup (Real Example)
Here's a real working example from a v0cl.one user:
{
"mcpServers": {
"coolify-enhanced": {
"command": "node",
"args": ["coolify-mcp-enhanced/dist/index.js"],
"env": {
"COOLIFY_ACCESS_TOKEN": "17|your-actual-token-here",
"COOLIFY_BASE_URL": "https://s1.v0cl.one"
},
"disabled": false,
"autoApprove": [
"list_servers",
"list_services",
"list_projects",
"list_applications",
"list_databases",
"get_server",
"get_service",
"get_application",
"get_database",
"create_project",
"create_fullstack_project",
"deploy_infrastructure_stack",
"get_application_resources",
"get_application_logs",
"get_deployments"
]
}
}
}
Cursor IDE Setup
# In Cursor, add MCP server:
env COOLIFY_ACCESS_TOKEN="0|your-token" COOLIFY_BASE_URL="https://your-server.com" node /path/to/coolify-mcp-enhanced/dist/index.js
Other MCP-Compatible Tools
The server works with any MCP-compatible AI tool. Just provide:
- Command:
node /path/to/coolify-mcp-enhanced/dist/index.js - Environment: Your
COOLIFY_ACCESS_TOKENandCOOLIFY_BASE_URL
💬 Example AI Conversations
Once set up, you can have natural conversations like:
🚀 Deploy a Full-Stack Application
"Create a new project called 'my-webapp' and deploy it with PostgreSQL database, Redis cache, and MinIO storage on my Coolify server."
📊 Monitor Your Applications
"Show me all my applications and their current resource usage. If any app is using more than 80% CPU, show me its recent logs."
🔧 Manage Environment Variables
"Update the environment variables for my 'api-server' application to include DATABASE_URL and REDIS_URL, then restart it."
🐳 Deploy Custom Services
"Deploy this Docker Compose configuration as a new service in my 'production' project."
🛠️ Available Tools & Commands
Project & Server Management
| Tool | Description | Example Use |
|---|---|---|
list_servers |
List all your Coolify servers | "Show me all my servers" |
list_projects |
List all projects | "What projects do I have?" |
create_project |
Create a new project | "Create a project called 'blog'" |
Application Management
| Tool | Description | Example Use |
|---|---|---|
list_applications |
List all applications | "Show all my apps" |
create_application |
Deploy new application | "Deploy my GitHub repo as an app" |
get_application_logs |
View application logs | "Show logs for my API server" |
get_application_resources |
Monitor resource usage | "How much CPU is my app using?" |
Infrastructure Deployment
| Tool | Description | Example Use |
|---|---|---|
create_fullstack_project |
Create project with common services | "Set up a full-stack project" |
deploy_infrastructure_stack |
Deploy PostgreSQL, Redis, MinIO | "Add database and cache to my project" |
Service Management
| Tool | Description | Example Use |
|---|---|---|
list_services |
List all services | "What services are running?" |
create_service |
Create new service | "Add a WordPress service" |
create_docker_compose_service |
Deploy Docker Compose | "Deploy this compose file" |
Database Management
| Tool | Description | Example Use |
|---|---|---|
list_databases |
List all databases | "Show my databases" |
create_database |
Create new database | "Create a PostgreSQL database" |
update_database |
Update database settings | "Change database memory limit" |
Environment & Configuration
| Tool | Description | Example Use |
|---|---|---|
get_application_environment_variables |
Get env vars | "Show environment variables" |
update_application_environment_variables |
Update env vars | "Update API keys" |
Deployment Management
| Tool | Description | Example Use |
|---|---|---|
get_deployments |
List deployments | "Show deployment history" |
cancel_deployment |
Cancel deployment | "Stop the failing deployment" |
deploy_application |
Deploy application | "Deploy my latest changes" |
🔧 Configuration Examples
Common Coolify Hosting Services
# Coolify Cloud (official)
export COOLIFY_BASE_URL="https://app.coolify.io"
# v0cl.one (popular hosting)
export COOLIFY_BASE_URL="https://s1.v0cl.one"
# or https://s2.v0cl.one, https://s3.v0cl.one, etc.
# Self-hosted Coolify
export COOLIFY_BASE_URL="https://coolify.yourdomain.com"
# Local development
export COOLIFY_BASE_URL="http://localhost:3000"
API Token Permissions
Your Coolify API token should have these permissions:
- ✅ Read servers - List and view server information
- ✅ Manage projects - Create and manage projects
- ✅ Manage applications - Deploy and manage applications
- ✅ Manage services - Create and manage services
- ✅ Manage databases - Create and manage databases
✅ Real-World Success Story
This enhanced MCP server has been successfully tested and deployed with a real v0cl.one Coolify instance:
Live Example Configuration
- Server:
https://s1.v0cl.one - Services Managed: Ghost blog, Docker registry, MySQL database
- Status: ✅ All enhanced tools working perfectly
- Performance: Real-time monitoring and management through AI
Verified Capabilities
- ✅ Server Management - Successfully lists and manages Coolify servers
- ✅ Service Monitoring - Real-time status of Ghost blog and Docker registry
- ✅ Database Management - MySQL database monitoring and management
- ✅ Enhanced Tools - All 15+ new tools tested and working
- ✅ AI Integration - Natural language commands working in Kiro IDE
What Users Are Saying
"The enhanced MCP server makes managing my v0cl.one Coolify instance incredibly easy. I can now deploy and monitor everything through simple AI conversations!"
🧪 Testing & Troubleshooting
Test Your Setup
# Basic connectivity test
node test-mcpaas.js
# Test specific functionality
echo '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"list_servers","arguments":{}}}' | node dist/index.js
Common Issues
❌ "Failed to connect to Coolify server"
- Check your
COOLIFY_BASE_URL- Make sure it's accessible - Verify your API token - Ensure it's valid and has permissions
- Check network connectivity - Ensure you can reach the server
❌ "Authentication required"
- Regenerate your API token in Coolify dashboard
- Check token format - Should start with
0|or similar - Verify token permissions - Ensure it has required scopes
❌ "Tool not found"
- Rebuild the server - Run
npm run build - Check MCP client configuration - Ensure correct path and environment
Debug Mode
# Enable detailed logging
DEBUG=coolify:* node dist/index.js
🤝 Contributing
We welcome contributions! This enhanced server builds upon the excellent foundation of the original Coolify MCP Server.
- Fork the repository
- Create a feature branch
- Add tests for new functionality
- Submit a pull request
📚 Documentation
- Original Coolify MCP Server - The foundation this builds upon
- Coolify Documentation - Learn about Coolify platform
- MCP Specification - Model Context Protocol details
📄 License
MIT License - Enhanced version maintains the same license as the original.
🙏 Acknowledgments
- Stuart Mason - Original Coolify MCP Server creator
- Coolify Team - Amazing self-hosting platform
- Anthropic - Model Context Protocol specification
🔗 Links
Ready to supercharge your Coolify workflow with AI? 🚀 Get started now!
Made with ❤️ for the Coolify community
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.