Enables agent-native desktop control by driving mouse, keyboard, and interface elements through accessibility-first semantic operations, with fallback to screen coordinates when accessibility cannot reach a target.
Local Windows MCP server for guarded x64dbg/x32dbg sessions: target identity by SHA-256, breakpoints, verified memory writes, runtime capture, PE dumps, and IDA evidence using module RVAs.
Enables ChatGPT in Chat mode to read and write local files, view the screen, and control the macOS desktop, with target locking and local permission controls.
An unofficial experimental local MCP server that lets AI clients work with an already logged-in Windows Weixin desktop client, providing bounded conversation and message reads, group and message search, polling of up to 16 selected chats, guarded text and attachment submission, and image/file viewing handoffs. It also exposes hybrid Computer Use prompts for native mention handoffs, while remeasuring the window, DPI, and target controls on each action and failing closed when evidence is insufficient.
Enables pixel-accurate mouse control, full keyboard and Unicode typing, screenshot capture, and an OCR element tree with bounding boxes on a remote GLKVM/PiKVM target, driven over its HTTPS API with no agent installed on the machine. It also detects concurrent human input and offers opt-in USB mass-storage file push/pull.
Enables secure, deny-by-default automation of Windows windows with per-action permissions, allowing observation, clicking, typing, and dragging on approved applications while verifying target identity and focus at runtime.
A lightweight Windows automation MCP server that scopes UI operations to a single target window, offering tools like ReadWindow, PeekWindow, Click, Type, Scroll, Screenshot, and App management with reduced token usage compared to full-desktop alternatives.
Enables agents to run Bash commands or argv on a target node, manage long-running jobs, and search files with ripgrep through DreamMate, returning native MCP structuredContent and JSON.
Enables AI agents to operate websites and Windows desktop applications by reading and acting on webpage elements, exposed UI controls, and screenshots with mouse and keyboard input. Combines browser, desktop, and computer-control channels in a single task, with an optional target selector for batched actions.
An MCP server for remotely controlling touchscreens on Linux devices over SSH using virtual touch input. It enables actions like tapping and swiping without requiring any software installation on the target machine.
Enables Claude Code to drive macOS apps in the background through the computer-use engine bundled with the ChatGPT desktop app, sending clicks, drags, keystrokes, menu bar and notification interactions to target apps while the user's cursor, windows and other work stay untouched.
A direct kernel debugger MCP server for Windows security research that connects to VM kernels via kdnet using DbgEng COM interfaces. It exposes over 60 tools for memory inspection, breakpoint management, and coordinated execution control between the host and target VM.