YingDao RPA MCP Server

影刀RPA: An RPA low-code platform, a product that everyone can use for RPA automation, which can free people from repetitive labor.

影刀AI Power: An AI low-code platform that allows for the quick creation of AI agents and AI workflows, helping users to utilize AI.

The YingDao RPA MCP Server is implemented based on the Model Context Protocol (MCP), providing the capability to call RPA for YingDao AI Power and other tools that can act as MCP Hosts (such as Claude Desktop, Cursor, etc.).

It supports both SSE Server and Stdio Server modes.

Getting Started

There are two ways to run YingDao RPA:

Local Mode

Set environment variables
Note: In local mode, only "My Acquired Apps" that have been executed at least once can be intelligently retrieved and run.
bash
RPA_MODEL=local
SHADOWBOT_PATH={your_shadowbot_path} // Path to the YingDao RPA .exe file
USER_FOLDER={your_user_folder} // Path to the YingDao RPA user folder

Path to the YingDao RPA .exe File

Windows
Note: On Windows, in the AI Power client, use double backslashes for the path.
bash
D:\Program Files\{installation_directory}\ShadowBot.exe

Mac

bash
/Applications/影刀.app

Path to the YingDao RPA User Folder

Find the user folder option in the settings of YingDao RPA.

Open API Mode (For Enterprise Users Only)

Set environment variables

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

How to Obtain

Enterprise administrators can log into the YingDao RPA console to obtain these. Please refer to YingDao RPA Help Documentation - Authentication.

Starting Stdio Server

Configure in the client
json
{
"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

Build

Clone the repository and build:

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

Configuration

Add an .env file, with configuration items as described above.

Start

bash
npm run start:server

Client Configuration

AI Power client configuration
json
{
"mcpServers": {
"YingDao RPA MCP Server": {
"url": "http://localhost:3000/sse",
"description": "YingDao MCP Server"
}
}
}

The default port is 3000.

Capabilities

Local Mode

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

Open API Mode

1. uploadFile: Upload files to the RPA platform
2. queryRobotParam: Query parameters of the RPA application
3. queryApplist: Get 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 RPA robots for scheduling

License

MIT