Dify Workflow MCP server

This TypeScript implementation of a Model Context Protocol (MCP) server enables you to expose Dify workflows as tools for AI systems. It creates a bridge between Dify applications and any system supporting the MCP standard.

Prerequisites

• Node.js 18 or higher
• npm 8 or higher
• Access to Dify API and application secret keys

Installation

Via Smithery

For automatic installation through Smithery:

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

Manual Installation

1. Clone the repository:

   git clone https://github.com/localSummer/dify-workflow-mcp
   cd dify-workflow-mcp
   

2. Install dependencies:

   npm install
   

3. Create a configuration file:

   # config.yaml
   dify_base_url: 'https://api.dify.ai/v1'
   dify_app_sks:
     - 'your-dify-app-sk-1' # Replace with your actual Dify application key
     - 'your-dify-app-sk-2' # Replace with your actual Dify application key
   

Usage

1. Build the project:

   npm run build
   

2. Start the server:

   npm start
   

Development Environment

To run in development mode:

npm run dev

Configuration

The server uses a YAML file for configuration. By default, it looks for config.yaml in the project root directory. You can specify a different path using the CONFIG_PATH environment variable.

Configuration Options

• dify_base_url: Base URL for the Dify API
• dify_app_sks: List of Dify application secret keys

Client Configuration

For Cline/Roo Code configuration:

"dify-workflow-mcp": {
   "command": "node",
   "args": [
      "path/dify-workflow-mcp/build/index.js"
   ],
   "env": {
      "CONFIG_PATH": "path/dify-workflow-mcp/config.yaml"
   },
   "disabled": false,
   "alwaysAllow": [],
   "timeout": 300
}

Important Notes

• The current workflow runs in blocking response mode, waiting for complete execution before returning results
• The workflow output fields are currently set to code and checkResult. If your output fields differ, you'll need to modify this code:

  const { code, checkResult } = responseData.data.outputs;
  

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "dify-workflow-mcp" '{"command":"node","args":["path/dify-workflow-mcp/build/index.js"],"env":{"CONFIG_PATH":"path/dify-workflow-mcp/config.yaml"},"disabled":false,"alwaysAllow":[],"timeout":300}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "dify-workflow-mcp": {
            "command": "node",
            "args": [
                "path/dify-workflow-mcp/build/index.js"
            ],
            "env": {
                "CONFIG_PATH": "path/dify-workflow-mcp/config.yaml"
            },
            "disabled": false,
            "alwaysAllow": [],
            "timeout": 300
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "dify-workflow-mcp": {
            "command": "node",
            "args": [
                "path/dify-workflow-mcp/build/index.js"
            ],
            "env": {
                "CONFIG_PATH": "path/dify-workflow-mcp/config.yaml"
            },
            "disabled": false,
            "alwaysAllow": [],
            "timeout": 300
        }
    }
}

3. Restart Claude Desktop for the changes to take effect