Dify Workflows

by jerryokk

3 stars
Not rated
GitHub

About

Enables dynamic tool discovery and execution across multiple Dify AI applications by automatically loading application configurations and converting input parameters to JSON schemas for robust workflow management.

Details

Author
jerryokk
Repository
jerryokk/dify-workflow-mcp
GitHub stars
3
Categories
Productivity, Developer Tools, Design, AI, Search, Infrastructure

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Dify Workflows
    Command (node, npx, python, etc.) node
    Arguments
    • Argument 1 path/dify-workflow-mcp/build/index.js
    • Argument 2 --base-url
    • Argument 3 https://api.dify.ai/v1
    • Argument 4 --api-keys
    • Argument 5 your-key-1,your-key-2,your-key-3

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "dify workflows": {
            "cwd": "path/dify-workflow-mcp",
            "env": {},
            "args": [
                "path/dify-workflow-mcp/build/index.js",
                "--base-url",
                "https://api.dify.ai/v1",
                "--api-keys",
                "your-key-1,your-key-2,your-key-3"
            ],
            "command": "node"
        }
    }
}

Linux

{
    "cwd": "path/dify-workflow-mcp",
    "env": [],
    "args": [
        "path/dify-workflow-mcp/build/index.js",
        "--base-url",
        "https://api.dify.ai/v1",
        "--api-keys",
        "your-key-1,your-key-2,your-key-3"
    ],
    "command": "node"
}

Macos

{
    "cwd": "path/dify-workflow-mcp",
    "env": [],
    "args": [
        "path/dify-workflow-mcp/build/index.js",
        "--base-url",
        "https://api.dify.ai/v1",
        "--api-keys",
        "your-key-1,your-key-2,your-key-3"
    ],
    "command": "node"
}

Windows

{
    "cwd": "path/dify-workflow-mcp",
    "env": [],
    "args": [
        "path/dify-workflow-mcp/build/index.js",
        "--base-url",
        "https://api.dify.ai/v1",
        "--api-keys",
        "your-key-1,your-key-2,your-key-3"
    ],
    "command": "node"
}

Dify Workflows MCP 服务器 (TypeScript)

一个 Model Context Protocol (MCP) 服务器的 TypeScript 实现,将 Dify 工作流作为工具暴露出来。 > 注意: 本项目基于 localSummer/dify-workflow-mcp 项目,并进行了一些修改和优化。

特性

- 将 Dify 应用程序转换为 MCP 工具 - 支持从 Dify 工作流流式响应(待实现) - 通过命令行参数进行配置 - 使用 TypeScript 编写,具有类型安全性

前提条件

- Node.js 18 或更高版本 - npm 8 或更高版本 - 访问 Dify API 和应用程序密钥

安装

1. 克隆仓库: ``bash git clone https://github.com/jerryokk/dify-workflow-mcp cd dify-workflow-mcp ` 2. 安装依赖: `bash npm install `

使用方法

1. 构建项目:
`bash npm run build ` 2. 启动服务器: `bash # 使用自定义参数 node build/index.js --base-url https://api.dify.ai/v1 --api-keys your-key-1,your-key-2,your-key-3 # 或使用默认示例参数 npm run start ` 开发环境: ``bash
No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.