@wallacewen/dify-mcp-server/README.md

Model Context Protocol server for Dify AI integration - supports server management, monitoring, and system tools

# Dify MCP Server

[![npm version](https://badge.fury.io/js/@wallacewen%2Fdify-mcp-server.svg)](https://badge.fury.io/js/@wallacewen%2Fdify-mcp-server)
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)

A Model Context Protocol (MCP) server that integrates with Dify AI to provide server management, monitoring, and system administration tools through conversational AI.

## Features

- 🧹 **Log Cleaning**: Automated server log cleaning and maintenance
- 🚀 **Server Deployment**: Environment deployment and Jenkins integration  
- 📊 **Server Monitoring**: Real-time server resource monitoring (CPU, memory, disk)
- 🔧 **System Tools**: Network connectivity checks, port monitoring, and system utilities
- 🔒 **Secure Configuration**: Environment-based configuration for sensitive data
- 🎯 **MCP Compatible**: Works with Claude Desktop and other MCP clients

## Installation

```bash
npm install -g @wallacewen/dify-mcp-server
```

Or with pnpm:

```bash
pnpm add -g @wallacewen/dify-mcp-server
```

## Configuration

### Required Environment Variables

Before using the server, you must configure these environment variables:

| Variable | Description | Required |
|----------|-------------|----------|
| `DIFY_API_TOKEN` | Your Dify API authentication token | ✅ |
| `DIFY_BASE_URL` | Base URL of your Dify instance | ✅ |
| `DIFY_DEFAULT_USER` | Default user ID for Dify API requests | ✅ |

### Environment Setup

Create a `.env` file or set environment variables:

```bash
# .env file
DIFY_API_TOKEN=your_dify_api_token_here
DIFY_BASE_URL=https://your-dify-instance.com
DIFY_DEFAULT_USER=your_user_id_here
```

Or export them in your shell:

```bash
export DIFY_API_TOKEN="your_dify_api_token_here"
export DIFY_BASE_URL="https://your-dify-instance.com"
export DIFY_DEFAULT_USER="your_user_id_here"
```

### Claude Desktop Configuration

Add the server to your Claude Desktop configuration file:

**macOS**: `~/Library/Application Support/Claude/claude_desktop_config.json`
**Windows**: `%APPDATA%\Claude\claude_desktop_config.json`

```json
{
  "mcpServers": {
    "dify-server": {
      "command": "dify-mcp-server",
      "env": {
        "DIFY_API_TOKEN": "your_dify_api_token_here",
        "DIFY_BASE_URL": "https://your-dify-instance.com",
        "DIFY_DEFAULT_USER": "your_user_id_here"
      }
    }
  }
}
```

## Usage

Once configured, the server provides the following tools through your MCP client:

### 🧹 Log Cleaning (`dify_log_clean`)

Clean server logs and manage log files:

```
Query: "清理服务器日志，10.0.19.41"
Query: "清理10.0.19.41 /var/log 目录下的旧日志文件"
```

### 🚀 Server Deployment (`dify_server_deployment`)

Manage server deployments and Jenkins integration:

```
Query: "服务器环境到jenkins"
Query: "配置生产环境jenkins"
```

### 📊 Server Monitoring (`dify_server_monitoring`)

Monitor server resources and performance:

```
Query: "查看服务器10.0.19.41的CPU和内存使用情况"
Query: "监控生产环境服务器资源状态"
```

### 🔧 System Tools (`dify_system_tools`)

Execute system utilities and checks:

```
Query: "检查网络连通性ping baidu.com"
Query: "查看磁盘空间df -h"
Query: "检查端口8080占用netstat -tulpn | grep 8080"
```

## Development

### Prerequisites

- Node.js >= 18.0.0
- pnpm (recommended) or npm

### Setup

1. Clone the repository:
```bash
git clone https://github.com/wallacewen/dify-mcp-server.git
cd dify-mcp-server
```

2. Install dependencies:
```bash
pnpm install
```

3. Set up environment variables:
```bash
cp .env.example .env
# Edit .env with your configuration
```

4. Build the project:
```bash
pnpm run build
```

5. Run in development mode:
```bash
pnpm run dev
```

### Testing

Run the test suite:

```bash
pnpm test
```

Run tests with coverage:

```bash
pnpm run test:coverage
```

### Code Quality

Format code:
```bash
pnpm run format
```

Lint code:
```bash
pnpm run lint
```

Type check:
```bash
pnpm run check-types
```

Run all checks:
```bash
pnpm run ci
```

## How to Get Dify Configuration

### 1. Get Your Dify API Token

1. Log in to your Dify instance
2. Go to your application settings
3. Navigate to the "API Access" section
4. Copy your API key

### 2. Get Your Dify Base URL

This is the base URL of your Dify instance, for example:
- `https://api.dify.ai` (for Dify Cloud)
- `https://your-domain.com` (for self-hosted)

### 3. Get Your User ID

The user ID can be found in:
- Your Dify application logs
- API response headers
- Contact your Dify administrator

## Troubleshooting

### Common Issues

**Missing Environment Variables**
```
❌ Missing required environment variables:
   DIFY_API_TOKEN
   DIFY_BASE_URL
   DIFY_DEFAULT_USER
```

Solution: Ensure all required environment variables are set correctly.

**Connection Errors**
- Verify your `DIFY_BASE_URL` is correct and accessible
- Check your `DIFY_API_TOKEN` is valid and has proper permissions
- Ensure your network allows connections to the Dify instance

**Authentication Errors**
- Verify your API token is correct
- Check if the token has expired
- Ensure the user ID has proper permissions

## Contributing

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Add tests for new functionality
5. Run the test suite
6. Submit a pull request

## License

MIT © [Wallace Wen](https://github.com/wallacewen)

## Support

- 🐛 [Report Issues](https://github.com/wallacewen/dify-mcp-server/issues)
- 💬 [Discussions](https://github.com/wallacewen/dify-mcp-server/discussions)
- 📧 Contact: wallacewen@example.com