What are the prerequisites for using Total PC Control?
Node.js 16 or higher, npm or yarn, and cmake-js (installed globally) are required. Additionally, the libnut core library must be built locally.
@jasondsmith72
Basic information
Total PC Control MCP server - v2 with fixes and compression
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"total-pc-control": {
"command": "node",
"args": [
"/ABSOLUTE/PATH/TO/total-pc-control/build/index.js"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Total PC Control is an MCP (Model Context Protocol) server that provides programmatic control over your screen, mouse, and keyboard using nut.js. It is designed for users who want to enable AI models (via MCP-compatible clients like Claude for Desktop) to perform direct computer interactions such as screen capture, mouse movement, typing, window management, and clipboard operations.
After cloning the repository, install cmake-js globally, build the libnut core library, then install dependencies and build the project. Configure your MCP client (e.g., Claude for Desktop) by editing its configuration file to point to the built build/index.js file and restart the client. The hammer icon in Claude indicates available tools.
Node.js 16 or higher, npm or yarn, and cmake-js (installed globally) are required. Additionally, the libnut core library must be built locally.
The README explicitly warns that giving AI models direct control over your computer can lead to unintended consequences. The software controls your mouse, keyboard, and system functions, and you use it entirely at your own risk; the creators accept no responsibility for any damage or data loss.
The server relies on nut.js, which supports Windows, macOS, and Linux. Additionally, the UI Automation tools (get_ui_element_info, invoke_ui_element_action) work on Windows only.
Edit the Claude for Desktop configuration file (macOS: `~/Library/Application Support/Claude/claude_desktop_config.json`; Windows: `%APPDATA%\Claude\claude_desktop_config.json`) and add an entry for "total-pc-control" pointing to the absolute path of `build/index.js`. Restart Claude for Desktop.
Tools are grouped into Screen Capture, Mouse Control, Keyboard Input, Clipboard Operations, and UI Automation. Examples include `capture_screen`, `move_mouse`, `type_text`, `set_clipboard_text`, and `get_ui_element_info`. Full tool lists with parameters are in the README.

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student β in a fraction of the time. What once took a week, now takes one free period.
π The fast, Pythonic way to build MCP servers and clients.
Painless E2E Automation for Mobile and Web

Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov

Model Context Protocol Servers
Comments