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
31 stars

This MCP server plugin for Dify allows you to transform a Dify application into a Model Context Protocol (MCP) server, enabling integration with MCP clients like Cherry Studio. The plugin acts as a bridge between your Dify apps and MCP-compatible clients.

Installation Steps

Create a Dify Workflow App

First, you need to create a simple workflow application in Dify that will serve as the foundation for your MCP server.

Add an Endpoint with the MCP Server Plugin

  1. Navigate to the Endpoints section in your Dify dashboard
  2. Add a new endpoint and select the MCP Server plugin
  3. Configure the required input schema for your app

For chat applications, ensure your input schema includes appropriate fields. Here's an example schema for a weather information app:

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

Connecting to MCP Clients

Once your endpoint is configured, you can connect it to any MCP-compatible client. The plugin supports two connection protocols:

Using the Streamable HTTP Protocol (Recommended)

  1. Copy your endpoint URL from Dify
  2. In your MCP client (like Cherry Studio), select the Streamable HTTP protocol
  3. Paste the endpoint URL in the connection settings
  4. Configure any additional authentication if required

Using the Legacy SSE Protocol

  1. Copy your endpoint URL from Dify
  2. In your MCP client, select the SSE protocol option
  3. Paste the endpoint URL in the connection settings
  4. Complete the client-specific configuration

Security Considerations

Important: For security reasons, it's strongly recommended to use this plugin exclusively within your private network to protect your data and API connections.

Version Information

The current version of the MCP Server plugin is 0.0.3, which includes fixes for SSE-related error logging issues. Version 0.0.2 added support for the Streamable HTTP protocol.

For feature requests or issues, visit the GitHub repository.

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