Coolify MCP Server

Coolify MCP Server

Enables control and management of Coolify self-hosted PaaS instances, allowing you to deploy applications, manage databases, monitor servers, and execute operations directly from AI assistants.

Category
访问服务器

README

Coolify MCP Server

npm version License: MIT Node.js Version

A Model Context Protocol (MCP) server for Coolify API integration. Control your self-hosted PaaS directly from Claude, Kiro, or any MCP-compatible AI assistant.

🚀 Features

  • Complete API Coverage: Applications, Databases, Servers, Projects, Services, Teams, Deployments, Private Keys
  • MCP Resources: Direct resource access via coolify:// URIs
  • Version Detection: Automatic feature compatibility based on Coolify version
  • Rate Limiting: Built-in rate limit handling with retry logic
  • Minimal Dependencies: Only axios and MCP SDK
  • TypeScript: Full type safety

📦 Installation

From npm (recommended)

npm install -g coolify-mcp-server

From source

git clone https://github.com/YOUR_USERNAME/coolify-mcp-server.git
cd coolify-mcp-server
npm install
npm run build

⚙️ Configuration

Environment Variables

Variable Required Description
COOLIFY_BASE_URL Yes Your Coolify instance URL (e.g., https://coolify.example.com)
COOLIFY_TOKEN Yes API token from Coolify
COOLIFY_TEAM_ID No Team ID for multi-team setups

Getting an API Token

  1. Go to your Coolify instance
  2. Navigate to Keys & TokensAPI tokens
  3. Create a new token with required permissions:
    • read - For listing resources
    • write - For creating/updating resources
    • deploy - For deployment operations

🔧 Usage

With Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "coolify": {
      "command": "coolify-mcp",
      "env": {
        "COOLIFY_BASE_URL": "https://your-coolify.com",
        "COOLIFY_TOKEN": "your-api-token"
      }
    }
  }
}

With Kiro

Add to your .kiro/settings/mcp.json:

{
  "mcpServers": {
    "coolify": {
      "command": "coolify-mcp",
      "env": {
        "COOLIFY_BASE_URL": "https://your-coolify.com",
        "COOLIFY_TOKEN": "your-api-token"
      }
    }
  }
}

From Source

{
  "mcpServers": {
    "coolify": {
      "command": "node",
      "args": ["/path/to/coolify-mcp-server/build/index.js"],
      "env": {
        "COOLIFY_BASE_URL": "https://your-coolify.com",
        "COOLIFY_TOKEN": "your-api-token"
      }
    }
  }
}

🛠️ Available Tools

Version & Health

Tool Description
get_version Get Coolify version information
health_check Check API health status

Teams

Tool Description
list_teams List all accessible teams
get_team Get team details by ID
get_current_team Get current team details
get_current_team_members Get current team members

Servers

Tool Description
list_servers List all servers
create_server Create a new server
validate_server Validate server connection
get_server_resources Get server resource usage
get_server_domains Get server domains

Projects & Environments

Tool Description
list_projects List all projects
get_project Get project details
create_project Create a new project
list_environments List project environments
create_environment Create a new environment

Applications

Tool Description
list_applications List all applications
get_application Get application details
create_application Create a new application
start_application Start an application
stop_application Stop an application
restart_application Restart an application
deploy_application Deploy an application
execute_command Execute command in container
get_application_logs Get application logs

Services

Tool Description
list_services List all services
create_service Create a new service
start_service Start a service
stop_service Stop a service
restart_service Restart a service

Databases

Tool Description
list_databases List all databases
create_database Create a new database (PostgreSQL, MySQL, MongoDB, Redis)

Deployments

Tool Description
list_deployments List all deployments
get_deployment Get deployment details

Private Keys

Tool Description
list_private_keys List all SSH private keys
create_private_key Create a new SSH private key

📚 MCP Resources

Access data directly via MCP resources:

coolify://applications    - List all applications
coolify://databases       - List all databases
coolify://servers         - List all servers
coolify://projects        - List all projects
coolify://services        - List all services
coolify://teams           - List all teams
coolify://deployments     - List all deployments
coolify://private-keys    - List all private keys

💡 Example Prompts

Once configured, you can ask your AI assistant:

  • "List all my Coolify applications"
  • "Deploy the app with UUID abc123"
  • "Show me the logs for my-app"
  • "Create a new PostgreSQL database called mydb"
  • "What servers do I have in Coolify?"
  • "Restart the production application"

🤝 Contributing

Contributions are welcome! Please read our Contributing Guide for details.

  1. Fork the repository
  2. Create your feature branch (git checkout -b feature/amazing-feature)
  3. Commit your changes (git commit -m 'feat: add amazing feature')
  4. Push to the branch (git push origin feature/amazing-feature)
  5. Open a Pull Request

📝 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgments

📮 Support

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选