MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
Hardware mouse MCP server for AI agents on Windows x64. USB HID control and voice dictation; requires compatible uMouse hardware and firmware. 面向 AI 智能体的硬件鼠标 MCP:USB HID 控制与语音听写,需要兼容的 uMouse 设备与固件。
MIT ★ 404 -
Control your Mac with detailed mouse, keyboard, screen, and window management capabilities.
MIT ★ 416 -
MCP server for AI-driven macOS control — screenshots, mouse, keyboard, windows, and shell sessions
MIT ★ 3 -
mcp-linux-desktopgithub.com/wizardofweb125-lab/mcp-linux-desktopupdated this year
MCP server for full Linux desktop control — windows, mouse, keyboard, clipboard, audio, screenshots, OCR, notifications, accessibility tree.
MIT ★ 1 -
Mcp.ComputerUsegithub.com/tdav/Mcp.ComputerUseupdated this year
Windows computer-use MCP server. Gives an LLM agent (Claude Code, Claude Desktop, any MCP client) full control over a Windows machine: monitor screenshots, mouse, keyboard, files, process launch, PowerShell.
-
Unofficial Vizcom MCP: sketch rendering, reference variations, masked edits and shared boards—without mouse control. 非官方设计工作流 MCP|中英文文档|MIT
MIT ★ 1 -
mcp-serial-hid-kvmgithub.com/sunasaji/mcp-serial-hid-kvmupdated this year
MCP server that gives AI agents (Claude, etc.) full keyboard, mouse, and screen control of a physical PC via serial-hid-kvm. Includes OCR-based screen reading.
MIT ★ 6 -
Give Claude full desktop control on Linux/X11 — screenshot, mouse, keyboard, windows, clipboard, app launch. Zero-dependency MCP extension, MIT-licensed.
MIT -
Control another PC's desktop from Claude Code via MCP — screenshot, mouse, keyboard, SSH, files. For GUI work SSH can't reach on a remote machine.
MIT -
MCP server that lets AI agents control a real Windows PC and Android devices: mouse, keyboard, windows, UI automation, processes, adb
MIT ★ 2 -
mac-mcp-servergithub.com/laststance/mac-mcp-serverupdated this year
MCP Server for macOS automation via AppleScript - 44 tools for system control, window management, keyboard/mouse input, screenshots, UI automation, and more
npm MIT -
macos-computer-use-skillgithub.com/wimi321/macos-computer-use-skillupdated this year
Standalone MCP server that gives AI agents full GUI control over macOS — screenshots, mouse, keyboard, apps, clipboard, and multi-display. Zero private dependencies.
MIT ★ 20 -
A MCP server that bridges AI agents to the macOS desktop: the accessibility tree, synthetic mouse and keyboard input, screenshots, window and application control, the shell, preferences, launchd, processes, the filesystem and web scraping.
MIT -
computer use for ai agents on omarchy and hyprland: screenshots, mouse, keyboard, ocr, accessibility tree and window control. a claude code plugin and mcp server.
MIT -
Desktop automation MCP server — computer use for any AI agent: control screen, windows, mouse/keyboard, and Chrome via Model Context Protocol (stdio). Not a DSH plugin — DSH users install dsh-nuphus-mcp.
MIT ★ 334 -
MCP server for ArkKVM: lets AI agents see and control a physical machine over WebRTC – HDMI screenshots, USB keyboard/mouse, virtual media and Virtual USB Drive, from BIOS/UEFI to desktop. Python, aiortc.
MIT -
Lets AI agents see and control a desktop GUI: screenshots, OCR, mouse, keyboard, windows and accessibility-tree UI elements. One-shot JSON CLI or MCP server. Windows 10/11, and Linux on KDE Plasma 6 or GNOME 45+ (Wayland).
MIT ★ 1 -
A MCP server that bridges AI agents to the Windows desktop. UI Automation, synthetic mouse/keyboard input, screenshots, window and application control, PowerShell, the registry, processes, the filesystem, and web scraping. No computer-vision model is required: the agent perceives the UI through the Windows accessibility tree.
MIT ★ 17 -
Advanced MCP server for intelligent computer use automation and AI agent operator control. Supports mouse and keyboard input, window-relative vision and coordinates, Retina display, and screenshot-based debugging. Designed for AI-driven workflows, app and
npm MIT -
WinCU / Windows Computer Use / Computer Action / Windows MCP: an MCP server that lets AI models operate a Windows PC with screenshots, mouse, keyboard, clipboard, window control and UI Automation. Works with Claude, ChatGPT and other vision models.
MIT ★ 3 -
Stealth browser automation that actually works. Runs Camoufox (custom Firefox) in Docker with zero Chrome DevTools Protocol exposure, real OS-level mouse and keyboard input via PyAutoGUI, and a JSON HTTP API + MCP server to control it all remotely. Watch it live via noVNC.
WTFPL ★ 98 -
An MCP server that lets Claude Code use your Windows apps. It reads each window as text through the accessibility tree, presses, fills and selects controls through UI Automation without moving your mouse, and replies to every action with what changed. One exe under 200 KB, no admin rights, free (Apache-2.0). Tested on Windows 11 with Claude Code.
Apache-2.0 -
macos-desktop-controlgithub.com/d-wwei/macos-desktop-controlupdated this year
MCP Server for native macOS desktop automation. Screenshot, mouse, keyboard, window management. Works with Claude Code, Codex CLI, Gemini CLI, Cursor, and any MCP client.
MIT ★ 6 -
面向 AI Agent 的屏幕操作 MCP 服务器 — 截图 + 鼠标键盘控制,9 个工具经 Streamable HTTP 上的 JSON-RPC 2.0 暴露
Apache-2.0 ★ 2 -
Let an AI see and operate Windows apps cheaply, without stealing focus or moving your mouse. MCP server for Claude Code.
MIT ★ 18 -
Let AI models use your Windows computer through MCP: screenshots, mouse, keyboard, windows, UI Automation and OCR, with every monitor and every window's position made explicit to the model.
NOASSERTION