drio
Open app

mcp-server-dify

Source

Sample MCP Server for Dify AI

Catalog onlyCatalog onlySTDIO

Overview

mcp-server-dify is a Model Context Protocol Server designed for Dify AI, enabling large language models (LLMs) to interact with Dify AI's chat completion capabilities through a standardized protocol.

To use mcp-server-dify, install it via NPM and configure it with your Dify API credentials in the claude_desktop_config.json file.

  • Integration with Dify AI chat completion API - Restaurant recommendation tool (meshi-doko) - Support for conversation context - Streaming response support - TypeScript implementation
  1. Enabling chatbots to provide restaurant recommendations based on user queries.
  2. Facilitating LLMs to maintain conversation context during interactions.
  3. Streamlining API interactions for developers using Dify AI.

Add to your AI client

Use these steps to connect mcp-server-dify in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

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

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

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

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

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

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "mcp-server-dify-yuru-sha": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-server-dify-yuru-sha"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

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

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

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

FAQ

What is the purpose of mcp-server-dify?

It serves as a bridge for LLMs to utilize Dify AI's chat capabilities effectively.

How do I install mcp-server-dify?

You can install it using NPM with the command `npm install @modelcontextprotocol/server-dify`.

Is there a security concern with using this server?

Yes, ensure to keep your API credentials secure and use HTTPS for the API endpoint.

Developer tools