MCP DifyWorkflow

v1.0.0Coding Agentsstable

mcp-difyworkflow-server is an mcp server Tools application that implements the query and invocation of Dify workflows, supporting the on-demand operation of multiple custom Dify workflows.

aimcpmcp-server
Share:
60
Stars
0
Downloads
0
Weekly
0/5

What is MCP DifyWorkflow?

MCP DifyWorkflow is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp-difyworkflow-server is an mcp server tools application that implements the query and invocation of dify workflows, supporting the on-demand operation of multiple custom dify workflows.

mcp-difyworkflow-server is an mcp server Tools application that implements the query and invocation of Dify workflows, supporting the on-demand operation of multiple custom Dify workflows.

This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • mcp-difyworkflow-server is an mcp server Tools application t

Use Cases

Query and invoke Dify workflows
Custom workflow automation from agents
gotoolkits

Maintainer

LicenseApache-2.0
Languagego
Versionv1.0.0
UpdatedMay 6, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx mcp-difyworkflow

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use MCP DifyWorkflow

mcp-difyworkflow-server is a Go-based MCP server that enables AI agents to query and invoke Dify platform workflows on demand. It connects to your self-hosted or cloud Dify instance via its REST API and exposes each configured workflow as a callable MCP tool. Developers who have built custom AI workflows in Dify can surface them directly inside Claude or other MCP clients without writing any glue code.

Prerequisites

  • Go 1.21 or higher (to build the binary from source)
  • A running Dify platform instance with at least one published workflow
  • Dify workflow API keys (one per workflow, generated from the Dify dashboard)
  • An MCP-compatible client such as Claude Desktop
1

Clone and build the server

Clone the repository and compile the Go binary. You can use make build or go build directly.

git clone https://github.com/gotoolkits/mcp-difyworkflow-server.git
cd mcp-difyworkflow-server
go build .
# or: make build
2

Install the binary system-wide (optional)

Create a symbolic link so the binary is available on your PATH and can be referenced by name in the MCP config.

sudo ln -s $(pwd)/mcp-difyworkflow-server /usr/local/bin/mcp-difyworkflow-server
3

Gather your Dify workflow names and API keys

In the Dify dashboard, open each workflow you want to expose, go to API Access, and generate an API key. Note the workflow names you will assign — these are user-defined labels used in prompts. Names and keys must be listed in the same order in the environment variables.

4

Configure your MCP client

Add the server to your claude_desktop_config.json. The -base-url flag points to your Dify API endpoint. DIFY_WORKFLOW_NAME and DIFY_API_KEYS are comma-separated lists that correspond one-to-one.

{
  "mcpServers": {
    "mcp-difyworkflow-server": {
      "command": "mcp-difyworkflow-server",
      "args": ["-base-url", "http://localhost/v1"],
      "env": {
        "DIFY_WORKFLOW_NAME": "workflow-translator,workflow-genImage",
        "DIFY_API_KEYS": "appkey-xxxxxxxxxxxa,appkey-xxxxxxxxxxxb"
      }
    }
  }
}
5

Restart your MCP client and verify

Restart Claude Desktop (or your chosen MCP host). Ask it to list available tools to confirm the Dify workflows are registered correctly.

MCP DifyWorkflow Examples

Client configuration

Minimal claude_desktop_config.json entry for two Dify workflows — a translator and an image generator. Replace the base-url with your Dify instance address and supply real API keys.

{
  "mcpServers": {
    "mcp-difyworkflow-server": {
      "command": "mcp-difyworkflow-server",
      "args": ["-base-url", "http://localhost/v1"],
      "env": {
        "DIFY_WORKFLOW_NAME": "workflow-translator,workflow-genImage",
        "DIFY_API_KEYS": "appkey-xxxxxxxxxxxa,appkey-xxxxxxxxxxxb"
      }
    }
  }
}

Prompts to try

Once the server is running, use these prompts inside Claude Desktop to interact with your Dify workflows.

- "View the list of tools available for mcp-difyworkflow-server."
- "Execute the workflow named 'workflow-translator' with the input message: 'Hello, world!'"
- "Run the workflow-genImage workflow and generate an image of a mountain at sunset."
- "List all authorized Dify workflows I can use."

Troubleshooting MCP DifyWorkflow

The server reports 'command not found' when Claude Desktop tries to start it

Either provide the absolute path to the binary in the 'command' field, or create a symlink with: sudo ln -s /path/to/mcp-difyworkflow-server /usr/local/bin/mcp-difyworkflow-server

Workflow execution fails with an authentication error

Ensure DIFY_WORKFLOW_NAME and DIFY_API_KEYS have the same number of comma-separated entries in the same order, and that each API key was generated for the correct workflow in the Dify dashboard.

The Dify API returns a 404 on workflow invocation

Verify the -base-url flag matches your Dify instance's API base URL (e.g. http://localhost/v1 for a local install, or https://api.dify.ai/v1 for the cloud). Also confirm the target workflow is published and not in draft state.

Frequently Asked Questions about MCP DifyWorkflow

What is MCP DifyWorkflow?

MCP DifyWorkflow is a Model Context Protocol (MCP) server that mcp-difyworkflow-server is an mcp server tools application that implements the query and invocation of dify workflows, supporting the on-demand operation of multiple custom dify workflows. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install MCP DifyWorkflow?

Follow the installation instructions on the MCP DifyWorkflow GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with MCP DifyWorkflow?

MCP DifyWorkflow works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is MCP DifyWorkflow free to use?

Yes, MCP DifyWorkflow is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.

Browse More Coding Agents MCP Servers

Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "mcp-difyworkflow": { "command": "npx", "args": ["-y", "mcp-difyworkflow"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use MCP DifyWorkflow?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides