Yingdao RPA MCP server

The 影刀RPA MCP Server is a middleware implementation based on the Model Context Protocol (MCP) that enables RPA (Robotic Process Automation) capabilities for 影刀AI Power and other MCP hosts like Claude Desktop or Cursor. It supports both SSE Server and Stdio Server modes, allowing you to automate repetitive tasks.

Installation Options

You can run the 影刀RPA MCP Server in two different modes: Local Mode or Open API Mode.

Local Mode Setup

Local mode allows you to run RPA applications that you've accessed and executed at least once before.

Set the following environment variables:

RPA_MODEL=local
SHADOWBOT_PATH={your_shadowbot_path}  # Path to the 影刀RPA executable
USER_FOLDER={your_user_folder}        # Path to the 影刀RPA user folder

Specifying the 影刀RPA Executable Path

For Windows (note: use double backslashes in AI Power client):

D://Program Files//{installation_directory}//ShadowBot.exe

For Mac:

/Applications/影刀.app

Finding the User Folder Path

Locate the user folder option in the 影刀RPA settings.

Open API Mode Setup (Enterprise Users Only)

Set the following environment variables:

RPA_MODEL=openApi
ACCESS_KEY_ID={your_access_key_id}
ACCESS_KEY_SECRET={your_access_key_secret}

To obtain your access credentials, enterprise administrators should log into the 影刀RPA console. Refer to the 影刀RPA Help Documentation - Authentication.

Running the Server

Stdio Server Configuration

Configure in your client:

{
  "mcpServers": {
    "YingDao RPA MCP Server": {
      "command": "npx",
      "args": ["-y", "yingdao-mcp-server"],
      "env":{
        "RPA_MODEL":"openApi",
        "ACCESS_KEY_ID":"{your_access_key_id}",
        "ACCESS_KEY_SECRET":"{your_access_key_secret}"
      }
    }
  }
}

SSE Server Configuration

Building from Source

git clone https://github.com/ying-dao/yingdao_mcp_server.git
cd yingdao_mcp_server
npm install
npm run build

Configuration

Create a .env file with the configuration items described above.

Starting the Server

npm run start:server

Client Configuration

Configure in AI Power client:

{
  "mcpServers": {
    "YingDao RPA MCP Server": {
      "url": "http://localhost:3000/sse",
      "description": "影刀 MCP Server"
    }
  }
}

The default port is 3000.

Available Capabilities

Local Mode Functions

1. queryRobotParam: Query RPA application parameters
2. queryApplist: Query the list of RPA applications
3. runApp: Run an RPA application

Open API Mode Functions

1. uploadFile: Upload files to the RPA platform
2. queryRobotParam: Query RPA application parameters
3. queryApplist: Get a paginated list of RPA applications
4. startJob: Start an RPA job
5. queryJob: Query the status of an RPA job
6. queryClientList: Query the list of scheduled RPA robots

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

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

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.