
Dokploy MCP Server
Exposes Dokploy functionalities as tools consumable via the Model Context Protocol, allowing AI models and other applications to programmatically manage projects and applications on a Dokploy server.
README
Dokploy MCP Server
<img alt="Install in VS Code (npx)" src="https://img.shields.io/badge/VS_Code-VS_Code?style=flat-square&label=Install%20Dokploy%20MCP&color=0098FF">
Dokploy MCP Server exposes Dokploy functionalities as tools consumable via the Model Context Protocol (MCP). It allows MCP-compatible clients (e.g., AI models, other applications) to interact with your Dokploy server programmatically.
This server focuses exclusively on tools for direct Dokploy API operations, providing a clean and efficient interface for project and application management.
🛠️ Getting Started
Requirements
- Node.js >= v18.0.0 (or Docker)
- Cursor, VS Code, Claude Desktop, or another MCP Client
- A running Dokploy server instance
Install in Cursor
Go to: Settings
-> Cursor Settings
-> MCP
-> Add new global MCP server
Add this to your Cursor ~/.cursor/mcp.json
file. You may also install in a specific project by creating .cursor/mcp.json
in your project folder. See Cursor MCP docs for more info.
{
"mcpServers": {
"dokploy-mcp": {
"command": "npx",
"args": ["-y", "@ahdev/dokploy-mcp"],
"env": {
"DOKPLOY_URL": "https://your-dokploy-server.com/api",
"DOKPLOY_AUTH_TOKEN": "your-dokploy-api-token"
}
}
}
}
<details> <summary>Alternative: Use Bun</summary>
{
"mcpServers": {
"dokploy-mcp": {
"command": "bunx",
"args": ["-y", "@ahdev/dokploy-mcp"],
"env": {
"DOKPLOY_URL": "https://your-dokploy-server.com/api",
"DOKPLOY_AUTH_TOKEN": "your-dokploy-api-token"
}
}
}
}
</details>
<details> <summary>Alternative: Use Deno</summary>
{
"mcpServers": {
"dokploy-mcp": {
"command": "deno",
"args": ["run", "--allow-env", "--allow-net", "npm:@ahdev/dokploy-mcp"],
"env": {
"DOKPLOY_URL": "https://your-dokploy-server.com/api",
"DOKPLOY_AUTH_TOKEN": "your-dokploy-api-token"
}
}
}
}
</details>
Install in Windsurf
Add this to your Windsurf MCP config file. See Windsurf MCP docs for more info.
{
"mcpServers": {
"dokploy-mcp": {
"command": "npx",
"args": ["-y", "@ahdev/dokploy-mcp"],
"env": {
"DOKPLOY_URL": "https://your-dokploy-server.com/api",
"DOKPLOY_AUTH_TOKEN": "your-dokploy-api-token"
}
}
}
}
Install in VS Code
<img alt="Install in VS Code (npx)" src="https://img.shields.io/badge/VS_Code-VS_Code?style=flat-square&label=Install%20Dokploy%20MCP&color=0098FF"> <img alt="Install in VS Code Insiders (npx)" src="https://img.shields.io/badge/VS_Code_Insiders-VS_Code_Insiders?style=flat-square&label=Install%20Dokploy%20MCP&color=24bfa5">
Add this to your VS Code MCP config file. See VS Code MCP docs for more info.
{
"servers": {
"dokploy-mcp": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@ahdev/dokploy-mcp"],
"env": {
"DOKPLOY_URL": "https://your-dokploy-server.com/api",
"DOKPLOY_AUTH_TOKEN": "your-dokploy-api-token"
}
}
}
}
Install in Zed
Add this to your Zed settings.json
. See Zed Context Server docs for more info.
{
"context_servers": {
"dokploy-mcp": {
"command": {
"path": "npx",
"args": ["-y", "@ahdev/dokploy-mcp"]
},
"settings": {
"DOKPLOY_URL": "https://your-dokploy-server.com/api",
"DOKPLOY_AUTH_TOKEN": "your-dokploy-api-token"
}
}
}
}
Install in Claude Desktop
Add this to your Claude Desktop claude_desktop_config.json
file. See Claude Desktop MCP docs for more info.
{
"mcpServers": {
"dokploy-mcp": {
"command": "npx",
"args": ["-y", "@ahdev/dokploy-mcp"],
"env": {
"DOKPLOY_URL": "https://your-dokploy-server.com/api",
"DOKPLOY_AUTH_TOKEN": "your-dokploy-api-token"
}
}
}
}
Install in BoltAI
Open the "Settings" page of the app, navigate to "Plugins," and enter the following JSON:
{
"mcpServers": {
"dokploy-mcp": {
"command": "npx",
"args": ["-y", "@ahdev/dokploy-mcp"],
"env": {
"DOKPLOY_URL": "https://your-dokploy-server.com/api",
"DOKPLOY_AUTH_TOKEN": "your-dokploy-api-token"
}
}
}
}
Using Docker
The Docker container supports both stdio and HTTP transport modes, making it flexible for different deployment scenarios.
-
Build the Docker Image:
git clone https://github.com/andradehenrique/dokploy-mcp.git cd dokploy-mcp docker build -t dokploy-mcp .
-
Quick Start with Helper Script:
Use the provided helper script for easy Docker management:
# Run in HTTP mode (recommended for web apps) ./docker-examples.sh http # Run in stdio mode (for MCP clients) ./docker-examples.sh stdio # Use docker-compose ./docker-examples.sh compose-up # View available commands ./docker-examples.sh help
-
Manual Docker Commands:
Stdio Mode (for MCP clients):
docker run -it --rm \ -e DOKPLOY_URL=https://your-dokploy-server.com/api \ -e DOKPLOY_AUTH_TOKEN=your_token_here \ dokploy-mcp
HTTP Mode (for web applications):
docker run -it --rm \ -p 3000:3000 \ -e MCP_TRANSPORT=http \ -e DOKPLOY_URL=https://your-dokploy-server.com/api \ -e DOKPLOY_AUTH_TOKEN=your_token_here \ dokploy-mcp
-
Docker Compose:
Use the provided
docker-compose.yml
for production deployments:# Start HTTP service docker-compose up -d dokploy-mcp-http # View logs docker-compose logs -f dokploy-mcp-http
-
MCP Client Configuration:
For stdio mode (Claude Desktop, VS Code, etc.):
{ "mcpServers": { "dokploy-mcp": { "command": "docker", "args": [ "run", "-i", "--rm", "-e", "DOKPLOY_URL=https://your-dokploy-server.com/api", "-e", "DOKPLOY_AUTH_TOKEN=your_token_here", "dokploy-mcp" ] } } }
For HTTP mode (web applications):
Start the HTTP server first, then configure your client to connect to
http://localhost:3000/mcp
.
Install in Windows
The configuration on Windows is slightly different compared to Linux or macOS. Use cmd
as the command wrapper:
{
"mcpServers": {
"dokploy-mcp": {
"command": "cmd",
"args": ["/c", "npx", "-y", "@ahdev/dokploy-mcp"],
"env": {
"DOKPLOY_URL": "https://your-dokploy-server.com/api",
"DOKPLOY_AUTH_TOKEN": "your-dokploy-api-token"
}
}
}
}
Environment Variables
DOKPLOY_URL
: Your Dokploy server API URL (required)DOKPLOY_AUTH_TOKEN
: Your Dokploy API authentication token (required)
🚀 Transport Modes
This MCP server supports multiple transport modes to suit different use cases:
Stdio Mode (Default)
The default mode uses stdio for direct process communication, ideal for desktop applications and command-line usage.
# Run with stdio (default)
npx -y @ahdev/dokploy-mcp
# or
npm run start:stdio
HTTP Mode (Streamable HTTP)
Modern HTTP mode exposes the server via HTTP/HTTPS using the Streamable HTTP protocol (MCP 2025-03-26). Perfect for web applications and remote clients.
# Run with HTTP mode
npm run start:http
# or
npx -y @ahdev/dokploy-mcp --http
# or via environment variable
MCP_TRANSPORT=http npx -y @ahdev/dokploy-mcp
HTTP Server Endpoints:
- POST /mcp - Client-to-server requests
- GET /mcp - Server-to-client notifications
- DELETE /mcp - Session termination
- GET /health - Health check endpoint
Configuration:
- Default port:
3000
(override withPORT=8080
) - Uses modern Streamable HTTP protocol (MCP 2025-03-26)
- Session management with automatic cleanup
For detailed transport mode documentation and client examples, see TRANSPORT_MODES.md.
📚 Available Tools
This MCP server provides comprehensive tools for Dokploy project, application, and database management through 43 tools organized into three main categories:
🗂️ Project Management (6 tools)
Complete project lifecycle management including creation, updates, duplication, and deletion:
project-all
- List all projectsproject-one
- Get project detailsproject-create
- Create new projectsproject-update
- Update project configurationsproject-duplicate
- Duplicate projects with selective service copyingproject-remove
- Delete projects
🚀 Application Management (24 tools)
Comprehensive application lifecycle and configuration management:
Core Operations
- CRUD Operations: Create, read, update, delete applications
- Lifecycle Management: Deploy, redeploy, start, stop, reload applications
- Utility Operations: Move between projects, clean queues, refresh tokens
Git Provider Integrations
Support for multiple Git providers with specific configurations:
- GitHub Provider - Full GitHub integration with webhooks
- GitLab Provider - Complete GitLab project integration
- Bitbucket Provider - Bitbucket repository management
- Gitea Provider - Self-hosted Gitea integration
- Git Provider - Custom Git repository support
- Docker Provider - Direct Docker image deployment
Configuration Management
- Build Settings - Configure build types (Dockerfile, Heroku, Nixpacks, etc.)
- Environment Management - Environment variables and build arguments
- Monitoring Integration - Application monitoring and metrics
- Traefik Configuration - Load balancer and reverse proxy settings
🐘 PostgreSQL Database Management (13 tools)
Complete PostgreSQL database lifecycle management:
Core Database Operations
- CRUD Operations: Create, read, update, remove PostgreSQL databases
- Lifecycle Management: Deploy, start, stop, reload, rebuild databases
- Configuration Management: External ports, environment variables, status changes
- Project Management: Move databases between projects
Available PostgreSQL Tools
postgres-create
- Create new PostgreSQL databasespostgres-one
- Get database detailspostgres-update
- Update database configurationspostgres-remove
- Delete databasespostgres-deploy
- Deploy databasespostgres-start
- Start database instancespostgres-stop
- Stop database instancespostgres-reload
- Reload database configurationspostgres-rebuild
- Rebuild database instancespostgres-move
- Move databases between projectspostgres-changeStatus
- Change database statuspostgres-saveExternalPort
- Configure external database portspostgres-saveEnvironment
- Manage database environment variables
For detailed information about each tool, including input schemas, required fields, and usage examples, see TOOLS.md.
Tool Annotations
All tools include semantic annotations to help MCP clients understand their behavior:
- Read-Only Tools (
readOnlyHint: true
): Safe operations that only retrieve data - Destructive Tools (
destructiveHint: true
): Operations that modify or delete resources - Creation Tools (
destructiveHint: false
): Operations that create new resources - Idempotent Tools (
idempotentHint: true
): Operations safe to repeat - External API Tools (
openWorldHint: true
): All tools interact with Dokploy API
🏗️ Architecture
The Dokploy MCP Server is built using:
@modelcontextprotocol/sdk
: For creating the MCP server and defining tools- Node.js & TypeScript: As the underlying runtime and language
- Stdio Transport: Communicates with MCP clients over standard input/output (stdio)
- Dokploy API Integration: Direct interaction with Dokploy server's REST API
- Comprehensive Tool Coverage: Complete implementation of all Dokploy application and project endpoints
- Robust Error Handling: Centralized HTTP client with retry logic and structured error responses
- Schema Validation: Full Zod-based input validation matching OpenAPI specifications
- Tool Annotations: Semantic annotations (readOnlyHint, destructiveHint, etc.) for enhanced MCP client understanding
The server architecture supports:
- 43 Tools covering all project, application, and database management operations
- Multiple Git Providers (GitHub, GitLab, Bitbucket, Gitea, custom Git)
- Flexible Configuration for builds, deployments, and monitoring
- Type-Safe Operations with comprehensive TypeScript support
Each tool includes input validation, API integration, and structured response formatting for consistent MCP client interaction.
🔧 Development
Clone the project and install dependencies:
git clone https://github.com/andradehenrique/dokploy-mcp.git
cd dokploy-mcp
npm install
Build:
npm run build
Local Configuration Example
{
"mcpServers": {
"dokploy-mcp": {
"command": "npx",
"args": ["tsx", "/path/to/dokploy-mcp/src/index.ts"],
"env": {
"DOKPLOY_URL": "https://your-dokploy-server.com/api",
"DOKPLOY_AUTH_TOKEN": "your-dokploy-api-token"
}
}
}
}
Testing with MCP Inspector
npx -y @modelcontextprotocol/inspector npx @ahdev/dokploy-mcp
Documentation
- TOOLS.md - Complete tool reference with schemas and examples
- CONTRIBUTING.md - Contributing guidelines
🔧 Troubleshooting
MCP Client Errors
-
Try adding
@latest
to the package name. -
Make sure you are using Node v18 or higher to have native fetch support with
npx
. -
Verify your
DOKPLOY_URL
andDOKPLOY_AUTH_TOKEN
environment variables are correctly set.
🤝 Contributing
We welcome contributions! If you'd like to contribute to the Dokploy MCP Server, please check out our Contributing Guide.
🆘 Support
If you encounter any issues, have questions, or want to suggest a feature, please open an issue in our GitHub repository.
📄 License
This project is licensed under the MIT License.
推荐服务器

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。
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。
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。
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。

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。
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。
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。

e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。