Dify

Provides an MCP server to invoke Dify workflows from MCP clients by loading config, then triggering workflows via SKs.
  • typescript

0

GitHub Stars

typescript

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "mcp-mirror-yanxingliu_dify-mcp-server": {
      "command": "uv",
      "args": [
        "--directory",
        "${DIFY_MCP_SERVER_PATH}",
        "run",
        "dify_mcp_server"
      ],
      "env": {
        "CONFIG_PATH": "$CONFIG_PATH"
      }
    }
  }
}

You can run Dify workflows from any MCP client by using a dedicated MCP server that invokes the Dify tooling. This server accepts your configuration, then lets you trigger Dify actions through MCP-compatible clients with a simple, local runtime setup.

How to use

Prepare your configuration and start the MCP server from your client. You will save your Dify base URL and the Dify app SKs in a config file, then point your MCP client at the local server configuration. When you connect from a client, the MCP server will invoke the appropriate Dify workflow based on the SK you choose.

Two essential steps you will perform are creating the local config and configuring the MCP client to run the server. Your local configuration enables the MCP server to reach the Dify platform and select the correct workflow.

Example flow you will follow after setup:

  • Create a config.yaml with your Dify base URL and the app SKs
  • Start the MCP server via your MCP client using the provided runtime command and path to the config
  • From any MCP client, trigger Dify workflows by selecting the configured SKs and options supported by your workflows.

How to install

Prerequisites: you need a runtime capable of running the MCP server entry point (the example uses an MCP runtime named UV). Ensure you can run commands from your shell and that you have access to a place where you can store the configuration file.

  1. Create a local configuration file named config.yaml with your Dify settings.

  2. Run the MCP server by configuring your MCP client to start the server using the runtime and the server entry name shown in the examples.

  3. Point your MCP client to the configuration file you created so the server can load the Dify base URL and app SKs.

Configuration and usage notes

The configuration file must contain the Dify base URL and the list of app SKs. Different SKs map to different Dify workflows, so choose the SK that corresponds to the workflow you want to invoke.

The MCP client configuration must reference the runtime command and path to the server code, along with the path to your config.yaml via environment variables. This enables the MCP client to launch the server in the correct directory and load the settings.

Example flow details are provided in the installation section to help you verify the steps and ensure the server is reachable by your MCP clients.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational