📌Overview

Purpose: The framework is designed to facilitate communication between large language models (LLMs) and Dify AI through a standardized Model Context Protocol.

Overview: The mcp-server-dify serves as a Model Context Protocol server that enables seamless interaction with Dify AI's chat completion features. It allows developers to integrate advanced dialog capabilities and context management, ensuring a rich user experience.

Key Features:

• Integration with Dify AI: Connects effortlessly to Dify AI’s chat completion API, enabling dynamic conversational interactions.

• Restaurant Recommendation Tool: Known as meshi-doko, this feature provides users with personalized restaurant recommendations based on parameters like location and budget constraints.

• Support for Conversation Context: Maintains the state of the conversation, allowing for more coherent exchanges over multiple interactions.

• Streaming Response Support: Delivers responses in real-time, enhancing user engagement and satisfaction during conversations.

• TypeScript Implementation: The server is built with TypeScript, ensuring type safety and better maintainability of the codebase.

---

mcp-server-dify

Model Context Protocol Server for Dify AI. This server enables LLMs to interact with Dify AI's chat completion capabilities through a standardized protocol.

Features

• Integration with Dify AI chat completion API
• Restaurant recommendation tool (meshi-doko)
• Support for conversation context
• Streaming response support
• TypeScript implementation

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

With Claude Desktop

Add the following configuration to your claude_desktop_config.json:

{
  "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

Restaurant recommendation tool that interfaces with Dify AI:

Parameters:

• LOCATION (string): Location of the restaurant
• BUDGET (string): Budget constraints
• query (string): Query to send to Dify AI
• conversation_id (string, optional): For maintaining chat context

Development

# Initial setup
make setup

# Build the project
make build

# Format code
make format

# Run linter
make lint

License

This project is released under the MIT License.

Security

This server interacts with Dify AI using your provided API key. Ensure to:

• Keep your API credentials secure
• Use HTTPS for the API endpoint
• Never commit API keys to version control

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.