mcpField
T
Total PC Control

Total PC Control

Local
github.com/jasondsmith72Other1Updated 82w ago

About Total PC Control

Total PC Control is an MCP server for controlling the screen, mouse, and keyboard through nut.js. It is intended for MCP clients performing desktop automation and also includes Windows-only UI Automation tools.

Key features

  1. 01Capture full screens or selected regions
  2. 02Move, click, scroll, and drag the mouse
  3. 03Type text and press key combinations
  4. 04Inspect and manipulate application windows
  5. 05Read and write clipboard content

Use cases

  1. 01Capture a screen or a specific region
  2. 02Automate mouse and keyboard input
  3. 03Copy or paste text through the clipboard
  4. 04Inspect and operate Windows UI elements

MCP support

Exposes screen capture, mouse, keyboard, clipboard, window, and Windows UI Automation tools to MCP clients. The README warns that direct computer control can cause unintended actions.

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

Total PC Control

An MCP (Model Context Protocol) server that provides control over your screen, mouse, and keyboard using nut.js.

⚠️ Warning: Use with Caution

This software enables programmatic control of your mouse, keyboard, and other system operations. By using this software, you acknowledge and accept that:

  • Giving AI models direct control over your computer through this tool can lead to unintended consequences
  • The software can control your mouse, keyboard, and other system functions
  • You are using this software entirely at your own risk
  • The creators and contributors of this project accept NO responsibility for any damage, data loss, or other consequences that may arise from using this software

Features

  • 📷 Screen Capture: Capture screenshots of your entire screen or specific regions
  • 🖱️ Mouse Control: Move the mouse cursor, click, double-click, and scroll
  • ⌨️ Keyboard Input: Type text and press keyboard shortcuts
  • 🪟 Window Management: Find, focus, and manipulate application windows
  • 📋 Clipboard Access: Copy and paste text

Prerequisites

  • Node.js 16 or higher
  • npm or yarn
  • cmake-js (for building native dependencies)

Installation

  1. Clone the repository:
git clone https://github.com/jasondsmith72/total-pc-control.git
cd total-pc-control
  1. Install cmake-js globally (required for building native dependencies):
npm install -g cmake-js
  1. Install the libnut core library (required for nut.js):
git clone https://github.com/nut-tree/libnut.git libnut-core
cd libnut-core
npm install
cmake-js rebuild
cd ..
  1. Install dependencies and build the project:
npm install
npm run build

Using with Claude for Desktop

  1. Edit your Claude for Desktop configuration file:
  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  1. Add the following to your configuration:
{
  "mcpServers": {
    "total-pc-control": {
      "command": "node",
      "args": [
        "/ABSOLUTE/PATH/TO/total-pc-control/build/index.js"
      ]
    }
  }
}

Replace /ABSOLUTE/PATH/TO/ with the actual path to where you cloned the repository.

  1. Restart Claude for Desktop

  2. Look for the hammer icon in the Claude interface to indicate available tools.

Available Tools

Screen Capture
  • capture_screen: Capture the entire screen as an image. Supports format (png/jpeg) and quality (jpeg only) parameters.
  • capture_region: Capture a specific region of the screen. Requires left, top, width, height. Supports format and quality.
  • get_screen_size: Get the dimensions (width and height) of the screen.
Mouse Control
  • move_mouse: Move the mouse cursor to a specific x, y position.
  • get_mouse_position: Get the current x, y position of the mouse cursor.
  • click_mouse: Click the mouse at the current position. Optional button (left, middle, right).
  • click_at: Click the mouse at a specific x, y position. Optional button.
  • double_click: Double-click the mouse at the current position.
  • double_click_at: Double-click the mouse at a specific x, y position.
  • scroll_mouse: Scroll the mouse wheel. Requires direction (up/down). Optional amount.
  • drag_mouse: Drag the mouse from the current position to a target x, y position.
  • drag_mouse_from_to: Drag the mouse from a startX, startY position to an endX, endY position.
Keyboard Input
  • type_text: Type text at the current cursor position. Requires text.
  • type_text_with_delay: Type text with a delay between keystrokes. Requires text. Optional delayMs.
  • press_key: Press a specific keyboard key. Requires key.
  • press_key_shortcut: Press a keyboard shortcut (combination of keys). Requires keys array.
  • hold_key: Hold down a keyboard key. Requires key.
  • release_key: Release a held keyboard key. Requires key.
Clipboard Operations
  • get_clipboard_text: Get text from the clipboard.
  • set_clipboard_text: Set text to the clipboard. Requires text.
  • copy_selected_text: Copy selected text to clipboard and return it (uses Ctrl+C/Cmd+C).
  • paste_text: Paste text at current cursor position (uses Ctrl+V/Cmd+V). Requires text.
  • get_clipboard_image: Get image from the clipboard (if available) as base64 data.
UI Automation Tools (Windows Only)

These tools use Windows UI Automation via PowerShell to interact with UI elements.

  • get_ui_element_info: Finds a UI element within a specified window and returns its properties (Name, AutomationId, ClassName, ControlType, BoundingRectangle, IsEnabled, IsOffscreen, Value, Children).
    • Requires windowTitle (can be partial match).
    • Requires at least one of elementName, automationId, or className to find a specific element.
    • If no element identifier is provided, it lists the direct children of the window.
  • invoke_ui_element_action: Performs an action on a specified UI element.
    • Requires windowTitle.
    • Requires action (Click, SetValue, or Focus).
    • Requires at least one of elementName, automationId, or className.
    • Requires valueToSet (string) if action is SetValue.

Development

To run the server in development mode:

npm run dev

To run tests:

npm test

License

This project is licensed under the MIT License - see the LICENSE file for details.

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.