mcpField
M
Mcp Difyworkflow Server

Mcp Difyworkflow Server

Local
github.com/gotoolkitsAI & Agents62Updated 96w ago

About Mcp Difyworkflow Server

Mcp Difyworkflow Server is an MCP server for listing authorized Dify workflows and invoking a selected workflow with input. It is intended for MCP clients that need access to multiple configured Dify workflows.

Key features

  1. 01List authorized Dify workflows
  2. 02Invoke a selected workflow with input
  3. 03Configure workflow names and API keys

Use cases

  1. 01Show workflows available to an MCP client
  2. 02Run a configured translation workflow
  3. 03Invoke a selected workflow with a message

MCP support

Exposes tools to list authorized Dify workflows and execute a selected workflow. MCP clients can invoke configured workflows using their names and inputs.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

mcp-difyworkflow-server

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.

INSTALL

git clone https://github.com/gotoolkis/mcp-difyworkflow-server.git

# build by go
cd mcp-difyworkflow-server
go build .

## or use make build
make build

Configuration

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

    The base URL of the Dify platform api server url.

  • "command":"mcp-difyworkflow-server"

    You can specify the absolute path for the compiled binary, or create a symbolic link with:
    "sudo ln -s <gitWorkPath>/mcp-difyworkflow-server /usr/local/bin/mcp-difyworkflow-server"

  • DIFY_WORKFLOW_NAME、DIFY_API_KEYS

    Need to correspond one by one in order.
    Workflow name can be self-defined by the user in the Prompt, and the Workflow API Key needs to be generated for the corresponding workflow created on the Dify platform (refer to the relevant Dify documentation for how to generate the API KEY).

Usage

  • list_workflows
    List authorized workflows
  • execute_workflow
    Execute a specified workflow,args: workflow_name, input Note: The input variable name of the dify workflow should be defined by default as: "message"
Samples

prompt: 查看 mcp-difyworkflow-server 可使用的工具列表
prompt: 给我执行 dify 名为 workflow-translator 的工作流,输入的消息为“这是一条测试消息”

prompt: View the list of tools available for mcp-difyworkflow-server.
prompt: Execute the workflow named 'workflow-translator' for me, the input message is "This is a test message".

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.