Dify MCP Server

🚀 Dify Workflow Model Context Protocol (MCP) Server

A simple implementation of an MCP server for dify. It enables the invocation of Dify workflows by calling MCP tools.

🚀 Quick Start

This server offers an easy - to - use solution for invoking Dify workflows through MCP tools.

📰 Press Releases

• [2025/4/15] Now supports passing base_url and app_sks directly via environment variables, making it more convenient to use on cloud hosting platforms.

📦 Installation

The server can be installed via Smithery or manually.

Step 1: Prepare config.yaml or Environment Variable Configuration

You can configure the server by setting environment variables or creating a config.yaml file.

Method 1: Using Environment Variables (Recommended for Cloud Platforms)

Set the following environment variables:

export DIFY_BASE_URL="https://cloud.dify.ai/v1"
export DIFY_APP_SKS="app-sk1,app-sk2" # Comma-separated list of App SKs

• DIFY_BASE_URL: The base URL of the Dify API.
• DIFY_APP_SKS: A comma - separated list of App Secret Keys (SKs). Each SK typically corresponds to a different Dify workflow.

Method 2: Using config.yaml

Create a config.yaml file to store your Dify base URL and App SKs.

Example config.yaml:

dify_base_url: "https://cloud.dify.ai/v1"
dify_app_sks:
  - "app-sk1" # SK for Workflow 1
  - "app-sk2" # SK for Workflow 2
  # Add more SKs as needed

• dify_base_url: The base URL of the Dify API.
• dify_app_sks: A list of App Secret Keys (SKs). Each SK typically corresponds to a different Dify workflow.

You can quickly create this file using the following commands (adjust the path and values):

# Create the directory (if it doesn't exist)
mkdir -p ~/.config/dify-mcp-server

# Create the configuration file
cat > ~/.config/dify-mcp-server/config.yaml <<EOF
dify_base_url: "https://cloud.dify.ai/v1"
dify_app_sks:
  - "app-sk1"
  - "app-sk2"
EOF

Step 2: Install the MCP Server on the Client

Use the MCP server on the client according to the following configuration:

Using the uv command:

uv your_mcp_server_fn --arg name=value ...

Example Configuration:

{
  "mcpServers": {
    "dify-mcp-server": {
      "command": "uv",
      "args": [
        "--directory", "/Users/lyx/Downloads/dify-mcp-server",
        "run", "dify_mcp_server"
      ],
      "env": {
        "DIFY_BASE_URL": "https://cloud.dify.ai/v1",
        "DIFY_APP_SKS": "app-sk1,app-sk2"
      }
    }
  }
}

Finally, Enjoy Using

After completing the above configuration, you can use Dify tools in any MCP - supported client.