Dify MCP Server

What does “dify” MCP Server do?

The dify MCP (Model Context Protocol) Server is a bridge that connects AI assistants with Dify workflows, enabling them to interact with external data sources, APIs, and services. By exposing Dify workflow tools through the MCP interface, this server allows AI agents to trigger and manage Dify workflows programmatically. This enhances development workflows by letting AI systems query databases, manage files, or interact with APIs using Dify as the backend. The server supports configuration via environment variables or YAML files, making it adaptable for both cloud and local setups.

List of Prompts

No information provided about prompt templates in the repository.

List of Resources

No explicit resources documented in the repository or README.

List of Tools

No explicit list of tools found in the repository or README. There is reference to “tools of MCP” but no specific tool names or descriptions are provided.

Use Cases of this MCP Server

• Workflow Orchestration: Enables AI agents to trigger and control Dify workflows remotely, automating complex business or development processes.
• API Integration: Facilitates the connection between AI systems and external services through Dify, allowing seamless API calls and data retrieval.
• Cloud Workflow Access: Makes it easy to connect cloud-hosted Dify workflows to MCP-compatible clients, improving scalability and access.
• Environment-based Configuration: Supports both environment variable and YAML config setups, making it suitable for both local and cloud deployments.
• Centralized Workflow Management: Allows management and invocation of multiple Dify workflows from a single MCP server instance for streamlined operations.

How to set it up

Windsurf

1. Ensure prerequisites such as Node.js and uvx/uv are installed.

2. Prepare configuration via environment variables or a YAML file.

3. Add the Dify MCP Server to your configuration:

   {
     "mcpServers": {
       "dify-mcp-server": {
         "command": "uvx",
         "args": [
           "--from", "git+https://github.com/YanxingLiu/dify-mcp-server", "dify_mcp_server"
         ],
         "env": {
           "DIFY_BASE_URL": "https://cloud.dify.ai/v1",
           "DIFY_APP_SKS": "app-sk1,app-sk2"
         }
       }
     }
   }
   

4. Save and restart Windsurf.

5. Verify that the server is running and workflows are accessible.

Claude

1. Install uvx or uv and set up environment variables or a config file.

2. Add the following configuration to the Claude MCP client:

   {
     "mcpServers": {
       "dify-mcp-server": {
         "command": "uvx",
         "args": [
           "--from", "git+https://github.com/YanxingLiu/dify-mcp-server", "dify_mcp_server"
         ],
         "env": {
           "DIFY_BASE_URL": "https://cloud.dify.ai/v1",
           "DIFY_APP_SKS": "app-sk1,app-sk2"
         }
       }
     }
   }
   

3. Save, restart, and verify setup.

Cursor

1. Make sure uvx/uv is installed and environment variables are set or config.yaml is prepared.

2. Insert the server configuration in Cursor’s MCP config:

   {
     "mcpServers": {
       "dify-mcp-server": {
         "command": "uvx",
         "args": [
           "--from", "git+https://github.com/YanxingLiu/dify-mcp-server", "dify_mcp_server"
         ],
         "env": {
           "DIFY_BASE_URL": "https://cloud.dify.ai/v1",
           "DIFY_APP_SKS": "app-sk1,app-sk2"
         }
       }
     }
   }
   

3. Save and restart Cursor.

4. Confirm server operation.

Cline

1. Install uvx/uv and set environment variables or provide a config.yaml.

2. Add the Dify MCP Server to the MCP configuration:

   {
     "mcpServers": {
       "dify-mcp-server": {
         "command": "uvx",
         "args": [
           "--from", "git+https://github.com/YanxingLiu/dify-mcp-server", "dify_mcp_server"
         ],
         "env": {
           "DIFY_BASE_URL": "https://cloud.dify.ai/v1",
           "DIFY_APP_SKS": "app-sk1,app-sk2"
         }
       }
     }
   }
   

3. Save and restart Cline.

4. Check that Dify workflows are reachable.

Securing API Keys

Always use environment variables to store sensitive data such as API keys. Example configuration:

{
  "mcpServers": {
    "dify-mcp-server": {
      "command": "uvx",
      "args": [
        "--from", "git+https://github.com/YanxingLiu/dify-mcp-server", "dify_mcp_server"
      ],
      "env": {
        "DIFY_BASE_URL": "https://cloud.dify.ai/v1",
        "DIFY_APP_SKS": "${DIFY_APP_SKS}"  // Use system environment variable
      }
    }
  }
}

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "dify-mcp-server": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “dify-mcp-server” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Based on the available information, this MCP server offers basic but robust integration of Dify workflows into MCP-compatible platforms. However, documentation about prompts, resources, and tools is missing, which lowers its usability for advanced or standardized LLM interactions.

Our opinion

MCP Score: 4/10.
The dify-mcp-server is easy to set up and provides good cloud/local configuration support, but lacks documentation on prompts, resources, and tool capabilities, which limits its broader MCP utility.

MCP Score