Dify

Sample MCP Server for Dify AI

javascript

11

GitHub Stars

javascript

Language

4 months ago

First Indexed

3 weeks ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

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

You deploy and run a Model Context Protocol (MCP) server that bridges LLMs with Dify AI’s chat completion capabilities. This server enables you to use Dify AI within MCP-powered clients, supports conversation context, and can stream responses for a smooth interactive experience.

How to use

To connect an MCP client to the Dify-based server, configure your MCP client to launch the server as a stdio process. This lets your client send requests to the server and receive streaming responses. The setup below shows how to wire the MCP client to the server so you can chat with Dify AI through your preferred interface.

Configure your MCP client with the following command pattern to start the server locally via npx. This runs the MCP server directly without building a separate container. Replace the placeholders with your actual Dify API endpoint and API key.

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

Available tools

meshi-doko

Restaurant recommendation tool that interfaces with Dify AI to provide location-based, budget-aware dining suggestions. It accepts LOCATION, BUDGET, and a query string, and can maintain conversation context with an optional conversation_id.