Dify

What is dify-mcp-server?

dify-mcp-server is a Model Context Protocol (MCP) server designed to integrate Dify workflows. It enables the invocation of Dify workflows by acting as a tool within the MCP ecosystem.

How to use dify-mcp-server?

Installation can be done via Smithery or manually. Manual installation involves two main steps:

1. Prepare configuration: Configure the server using either environment variables (recommended for cloud platforms) or a config.yaml file. Environment variables include DIFY_BASE_URL and DIFY_APP_SKS (comma-separated). For config.yaml, a similar structure is used with a list of Dify App SKs.
2. Installation on your client: Use uvx (recommended, no code cloning needed) or uv (local clone + uv start) to run the server. Both methods involve setting environment variables or providing the path to the config.yaml file.

Key features of dify-mcp-server

• Dify Workflow Integration: Seamlessly connects with Dify workflows.
• MCP Compatibility: Functions as a tool within the Model Context Protocol.
• Flexible Configuration: Supports configuration via environment variables or config.yaml.
• Easy Deployment: Can be installed via Smithery or through simple uvx/uv commands.
• Cloud-friendly: Environment variable configuration makes it suitable for cloud-hosted platforms.

Use cases of dify-mcp-server

• Integrating Dify workflows into MCP-compatible clients: Allows any client supporting MCP to utilize Dify workflows as tools.
• Automating Dify workflow execution: Trigger Dify workflows programmatically through the MCP server.
• Centralized management of Dify App SKs: Configure multiple Dify App SKs for different workflows.

FAQ from dify-mcp-server

• How to pass base_url and app_sks? As of April 15, 2025, you can directly use environment variables for base_url and app_sks, which is convenient for cloud-hosted platforms.
• What is Smithery? Smithery is a platform for installing and managing servers, including dify-mcp-server.
• What is uv and uvx? uv and uvx are tools for installing and running Python packages and applications. uvx is recommended for its ability to run without cloning the code.

Model Context Protocol (MCP) Server for dify workflows

A simple implementation of an MCP server for using dify. It achieves the invocation of the Dify workflow by calling the tools of MCP.

📰 News

• [2025/4/15] zNow supports directly using environment variables to pass base_url and app_sks, making it more convenient to use with cloud-hosted platforms.

🔨Installation

The server can be installed via Smithery or manually.

Step1: prepare config.yaml or enviroments

You can configure the server using either environment variables or 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 your Dify App SKs

• DIFY_BASE_URL: The base URL for your Dify API.
• DIFY_APP_SKS: A comma-separated list of your Dify App Secret Keys (SKs). Each SK typically corresponds to a different Dify workflow you want to make available via MCP.

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 for your Dify API.
• dify_app_sks: A list of your Dify App Secret Keys (SKs). Each SK typically corresponds to a different Dify workflow.

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

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

# Create the config file
cat > ~/.config/dify-mcp-server/config.yaml <<EOF
dify_base_url: "https://cloud.dify.ai/v1"
dify_app_sks:
  - "app-your-sk-1"
  - "app-your-sk-2"
EOF

echo "Configuration file created at ~/.config/dify-mcp-server/config.yaml"

When running the server (as shown in Step 2), you will need to provide the path to this config.yaml file via the CONFIG_PATH environment variable if you choose this method.

Step2: Installation on your client

❓ If you haven't installed uv or uvx yet, you can do it quickly with the following command:

curl -Ls https://astral.sh/uv/install.sh | sh

✅ Method 1: Use uvx (no need to clone code, recommended)

{
"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",
    }
  }
}
}

or

{
"mcpServers": {
  "dify-mcp-server": {
    "command": "uvx",
      "args": [
        "--from","git+https://github.com/YanxingLiu/dify-mcp-server","dify_mcp_server"
      ],
    "env": {
       "CONFIG_PATH": "/Users/lyx/Downloads/config.yaml"
    }
  }
}
}

✅ Method 2: Use uv (local clone + uv start)

You can also run the dify mcp server manually in your clients. The config of client should like the following format:

{
"mcpServers": {
  "mcp-server-rag-web-browser": {
    "command": "uv",
      "args": [
        "--directory", "${DIFY_MCP_SERVER_PATH}",
        "run", "dify_mcp_server"
      ],
    "env": {
       "CONFIG_PATH": "$CONFIG_PATH"
    }
  }
}
}

or

{
"mcpServers": {
  "mcp-server-rag-web-browser": {
    "command": "uv",
      "args": [
        "--directory", "${DIFY_MCP_SERVER_PATH}",
        "run", "dify_mcp_server"
      ],
    "env": {
       "CONFIG_PATH": "$CONFIG_PATH"
    }
  }
}
}

Example config:

{
"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",
    }
  }
}
}

Enjoy it

At last, you can use dify tools in any client who supports mcp.