Total PC Control
@jasondsmith72
Total PC Control について
An MCP server that provides control over screen, mouse, and keyboard using nut.js
基本情報
設定
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"total-pc-control": {
"command": "node",
"args": [
"/ABSOLUTE/PATH/TO/total-pc-control/build/index.js"
]
}
}
}ツール
ツールは検出されませんでした
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
概要
What is Total PC Control?
Total PC Control is an MCP (Model Context Protocol) server that provides programmatic control over your screen, mouse, and keyboard using the nut.js library. It is designed for use with AI models, such as Claude for Desktop, enabling them to capture screenshots, move the cursor, type text, manage windows, and interact with the clipboard.
How to use Total PC Control?
Installation requires Node.js 16+, npm or yarn, and cmake-js installed globally. Clone the repository, build the libnut core library from source, then run npm install and npm run build. For Claude for Desktop, edit the claude_desktop_config.json file to add an MCP server entry with "command": "node" and "args" pointing to the absolute path of build/index.js. Restart Claude for Desktop and confirm the hammer icon appears.
Key features of Total PC Control
- Screen capture: capture full screen or a specific region
- Mouse control: move, click, double-click, right-click, and scroll
- Keyboard input: type text, press keys, hold and release keys
- Window management: find, focus, and get the active window
- Clipboard operations: copy and paste text
Use cases of Total PC Control
- AI agents performing automated desktop tasks like moving files or filling forms
- Testing and debugging applications by simulating mouse and keyboard input
- Automating repetitive workflows such as data entry or UI interactions
- Capturing screen content for analysis or documentation by AI models
FAQ from Total PC Control
Is using Total PC Control safe?
No, the software warns that giving AI models direct control over your computer can lead to unintended consequences. You use it entirely at your own risk, and the creators accept no responsibility for damage or data loss.
What are the system requirements?
Node.js 16 or higher, npm or yarn, and cmake-js (installed globally) are required. The libnut core library must be built from source during installation.
What dependencies does Total PC Control rely on?
It depends on the nut.js library for cross-platform mouse, keyboard, and screen operations, which in turn requires the libnut native core library.
How do I configure Total PC Control with Claude for Desktop?
Edit the Claude for Desktop configuration file (claude_desktop_config.json on macOS or Windows) to add an mcpServers entry with "command": "node" and "args" set to the absolute path of the built index.js file, then restart Claude for Desktop.
What tools does Total PC Control provide?
It offers tools for screen capture (capture_screen, capture_region), mouse control (move_mouse, click_mouse, double_click, right_click, scroll_mouse), keyboard input (type_text, press_key, hold_key, release_key), window management (find_window, focus_window, get_active_window), and clipboard operations (copy_to_clipboard, paste_from_clipboard).
「生産性」の他のコンテンツ
MCPControl
CheffromspaceMCP server for Windows OS automation
Lamda
firerpaAndroid Full-Stack Device Control Platform: WebRTC/H.264 remote desktop, UI/OCR/image-matching automation, one-click MITM, built-in Frida, proxy/VPN/frp/P2P networking, MCP/Agent, 160+ APIs, designed for multi-device clusters and engineered deployments.
MCP Google Calendar Server
markelaugust74A Model Context Protocol (MCP) server implementation for Google Calendar integration. Create and manage calendar events directly through Claude or other AI assistants.
Computer Control MCP
AB498MCP server that provides computer control capabilities, like mouse, keyboard, OCR, etc. using PyAutoGUI, RapidOCR, ONNXRuntime. Similar to 'computer-use' by Anthropic. With Zero External Dependencies.
MCP Shrimp Task Manager
cjo4m06Shrimp Task Manager is a task tool built for AI Agents, emphasizing chain-of-thought, reflection, and style consistency. It converts natural language into structured dev tasks with dependency tracking and iterative refinement, enabling agent-like developer behavior in reasoning A
コメント