Dify Workflow MCP server

Transforms Dify workflow applications into function-enabled endpoints, allowing AI tools to interact with custom functions through a simple setup process that bridges Dify's capabilities with external systems.
Back to servers
Provider
hjlarry
Release date
Mar 18, 2025
Language
Python
Stats
16 stars

The MCP Server plugin transforms your Dify application into a Model Context Protocol (MCP) server. This allows clients like Cherry Studio to connect to your Dify app and utilize it as a tool through the MCP protocol.

Installation

Creating a Dify App

  1. Create a simple workflow app in Dify.
  2. Add an endpoint and select this app.

The app's input schema must define input parameters. For a chat Dify app, include a query field in the input schema:

{
    "name": "get_weather",
    "description": "Get weather status for a place.",
    "inputSchema": {
        "properties": {
            "place": {"title": "Place", "type": "string"}
        },
        "required": ["place"],
        "title": "get_weatherArguments",
        "type": "object"
    }
}

Usage

Connecting to Cherry Studio

You can connect your MCP server to clients like Cherry Studio using one of two protocols:

Using the Streamable HTTP Protocol (Recommended)

  1. Copy your Dify endpoint URL
  2. In Cherry Studio, configure the connection using the Streamable HTTP protocol
  3. Enter your endpoint URL when prompted

Using the Legacy SSE Protocol

  1. Copy your Dify endpoint URL
  2. In Cherry Studio, configure the connection using the SSE protocol
  3. Enter your endpoint URL when prompted

Security Consideration

To maintain data security, it's strongly recommended to use this plugin exclusively within your private network.

Version Information

The current version is 0.0.2, which includes:

  • Support for the new Streamable HTTP protocol
  • Updated Dify plugin SDK version

How to add this MCP server to 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 > MCP and click "Add new global MCP server".

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

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

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 explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later