Dify.ai Workflow

🚀 Implementation of MCP Server for Dify Workflow

This is a simple implementation of invoking dify workflows, accomplished by calling MCP tools.

🚀 Quick Start

📦 Installation

This server can be installed via Smithery or manually. Both methods require preparing a config.yaml file.

📋 Prepare config.yaml

Before using the MCP server, you need to prepare a config.yaml file to store your dify_base_url and dify_sks configuration information. Here is an example configuration:

dify_base_url: "https://cloud.dify.ai/v1"
dify_app_sks:
  - "app-sk1"
  - "app-sk2"

Different SKs correspond to different Dify workflows.

🛠️ Installation via Smithery

smithery is a tool for automatically installing the Dify MCP server. To automatically install the Dify MCP server for Claude Desktop via Smithery:

npx -y @smithery/cli install dify-mcp-server --client claude

🛠️ Manual Installation

You can also manually run the Dify MCP server on the client. The client configuration should be as follows:

"mcpServers": {
  "mcp-server-rag-web-browser": {
    "command": "uv",
      "args": [
        "--directory", "${DIFY_MCP_SERVER_PATH}",
        "run", "dify_mcp_server"
      ],
    "env": {
       "CONFIG_PATH": "$CONFIG_PATH"
    }
  }
}

Example configuration:

"mcpServers": {
  "mcp-server-rag-web-browser": {
    "command": "uv",
      "args": [
        "--directory", "/Users/lyx/Downloads/dify-mcp-server",
        "run", "dify_mcp_server"
      ],
    "env": {
       "CONFIG_PATH": "/Users/lyx/Downloads/config.yaml"
    }
  }
}

💻 Usage Examples

Finally, you can use Dify tools in any MCP - supported client.