mcpField
A
aipower-rpa-mcp-server

aipower-rpa-mcp-server

Local
github.com/catinairProductivity1Updated 79w ago
Repository

About aipower-rpa-mcp-server

YingDao RPA MCP Server connects YingDao RPA capabilities to AI Power and other MCP Hosts. It is intended for workflows where AI needs to query or run RPA applications, and offers local and enterprise Open API modes with SSE and Stdio transports.

Key features

  1. 01Query RPA application parameters
  2. 02List RPA applications
  3. 03Run local RPA applications
  4. 04Start and check jobs through Open API
  5. 05Support SSE and Stdio modes

Use cases

  1. 01Let AI inspect available RPA applications
  2. 02Start a local RPA application through AI
  3. 03Launch and track jobs in enterprise Open API mode

MCP support

The MCP server exposes YingDao RPA tools to AI Power and MCP Hosts such as Claude Desktop and Cursor. It supports connections through SSE or Stdio.

#mathgpt#math-solver#math-assistant

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

README image

# YindDao AI Power - RPA MCP Server

[English] | [Chinese]

YingDao AI Power: An AI low-code platform that quickly creates AI agents and AI workflows, helping users leverage AI effectively.

YingDao RPA: An RPA low-code platform, a user-friendly RPA automation product that frees people from repetitive labor.

Yingdao RPA MCP Server is implemented based on the Model Context Protocol (MCP), providing a bridge for interaction between YindDao AI Power and other tools that can serve as MCP Hosts (such as Claude Desktop, Cursor, etc.). It enables AI to utilize RPA capabilities.

It supports both SSE Server and Stdio Server modes.

Getting Started

There are two ways to run YindDao RPA:

Local Mode

Set environment variables:

RPA_MODEL=local
SHADOWBOT_PATH={your_shadowbot_path} //Path to YindDao RPA executable
USER_FOLDER={your_user_folder}       //Path to YindDao RPA user folder
Path to YindDao RPA executable

Windows

D:\Program Files\{installation directory}\ShadowBot.exe

Mac

/Applications/影刀.app
Path to YindDao RPA user folder

Find the user folder option in YindDao RPA settings

User folder settings

Open API Mode (Enterprise users only)

Set environment variables:

RPA_MODEL=openApi
ACCESS_KEY_ID={your_access_key_id}
ACCESS_KEY_SECRET={your_access_key_secret}
How to obtain

Enterprise administrators can obtain this by logging into the YindDao RPA console. Please refer to YindDao RPA Help Documentation - Authentication

Stdio Server Startup

Configure in the client:

{
  "mcpServers": {
    "YingDao RPA MCP Server": {
      "command": "npx",
      "args": ["-y", "@automa-ai-power/rpa-mcp-servers", "-stdio"],
      "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:

git clone https://github.com/AutomaApp/aipower-rpa-mcp-server.git
cd aipower-rpa-mcp-servers
npm install
npm run build

Configuration

Add a .env file with configuration items as described above

Startup

npm run start:server

Client Configuration

AI Power client configuration:

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

The default port is 3000

Capabilities

Local Mode

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

Open API Mode

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

MIT

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.