MCP Server Dify

🚀 mcp-server-dify

A model context protocol server for Dify AI. This server enables large language models to interact with Dify AI's chat completion feature through a standardized protocol.

🚀 Quick Start

The mcp-server-dify is a server that allows large language models to interact with Dify AI's chat completion feature. It provides a standardized protocol for seamless integration.

✨ Features

• Integrates with Dify AI's chat completion API.
• Restaurant recommendation tool (meshi-doko).
• Supports conversation context.
• Provides streaming response support.
• Implemented in TypeScript.

📦 Installation

Using Docker

# Build the Docker image
make docker

# Run with Docker
docker run -i --rm mcp/dify https://your-dify-api-endpoint your-dify-api-key

💻 Usage Examples

Using with Claude Desktop

Add the following configuration to your claude_desktop_config.json file:

{
  "mcpServers": {
    "dify": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-dify",
        "https://your-dify-api-endpoint",
        "your-dify-api-key"
      ]
    }
  }
}

Replace your-dify-api-endpoint and your-dify-api-key with your actual Dify API credentials.

Tools

meshi-doko

A restaurant recommendation tool that interacts with Dify AI:

• LOCATION (string): The location of the restaurant.
• BUDGET (string): The budget limit.
• query (string): The question sent to Dify AI.
• conversation_id (string, optional): Used to maintain the chat context.

🔧 Technical Details

Development

# Initial setup
make setup

# Build the project
make build

# Format the code
make format

# Run checks
make lint

📄 License

This project is open-sourced under the MIT License.

🚧 Important Note

This server interacts with Dify AI using the API key you provide. Please ensure:

• Keep your API credentials secure.
• Use an HTTPS connection to the API endpoint.
• Never commit your API key to the version control system.

👥 Contribution

Contributions are welcome! Feel free to submit a Pull Request.