Enables OpenAI Codex to inspect and operate Windows desktop applications in the background while the user keeps control of the mouse, keyboard, and foreground window, with each action verified against the application's real state.
Enables printing files on Windows through Codex using natural-language requests or the /print quick command, supporting PDFs, Office documents, images, text, local paths, and UNC network paths with printer selection, previews, and job safeguards.
Enables AI agents to securely connect to and manage remote servers via SSH, with tools for running commands, file operations, log inspection, service management, and system monitoring under configurable access controls and audit logging.
Provides screen capture and optical character recognition (OCR) capabilities for entire displays or specific application windows. It enables users to list running applications, take screenshots, and extract text from images using multi-language support.
Enables ChatGPT to control a Windows PC remotely via OpenAI Secure MCP Tunnel, executing file operations, PowerShell commands, and system actions through a local MCP server.
A local agent that monitors your system clipboard, automatically uploads copied images to Supabase Storage, and replaces the clipboard content with the public URL for immediate sharing.
Enables AI coding agents like Claude to read Windows clipboard contents (text and images) from within WSL environments, providing seamless cross-platform clipboard access through the Model Context Protocol.
Enables an AI assistant to control a computer locally by viewing screens or windows, moving the mouse, clicking, dragging, scrolling, typing, pressing hotkeys, and using the clipboard.
An MCP server for intelligent Linux kernel configuration management and building. Enables AI assistants to generate, manage, and optimize kernel configurations and build kernels with comprehensive error detection.
Enables AI clients to control QEMU virtual machines over QMP and the human monitor, with text-first screen access via OCR text, ASCII rendering, or PNG screenshots. It supports launching and resetting VMs, typing text and sending key sequences, moving the mouse, creating disk images, and reading or building FAT images.
Enables ChatGPT Chat to operate an Apple Silicon Mac by running commands, reading and writing files, viewing the screen, driving app UIs, and accessing everyday apps through an OpenAI Secure MCP Tunnel while keeping machine-specific details local.
Enables local macOS computer use by letting agents click, type, and inspect accessibility trees without stealing focus, through an unofficial host for OpenAI Computer Use.
Enables MCP clients to observe Windows accessibility trees and deltas, generate fail-closed semantic action plans for external authorized executors, and control isolated, agent-owned Chrome tabs without accessing personal tabs.
Enables voice-controlled local automation and laser engraving, allowing users to generate engraving previews and G-code from spoken text and send jobs to a laser engraver after confirmation.
Enables ChatGPT to securely access project files and directories, read and write text files, and run allowlisted PowerShell commands on a Windows machine through an OpenAI Secure MCP Tunnel.
Wraps OpenAI Codex's computer-use engine to provide MCP tools for Windows screen operations including screenshot, UI automation tree, and input simulation, enabling Claude Code to control the desktop.
Enables AI assistants like Claude to manage Docker containers, images, and Docker Compose deployments through the Model Context Protocol. Provides secure container lifecycle management, image operations, and multi-host Docker server connections.
Restores OpenAI Codex Computer Use on macOS 13 by building a clean-room MCP backend that adapts to the bundled sky interface, enabling screen interaction and app control without modifying system libraries.
Enables MCP-compatible clients to inspect Windows images, edit NTLite presets, and run apply, save, and ISO creation operations through the running NTLite window.
A Windows-local MCP server for capturing screenshots (full screen, displays, regions, active window) and managing capture images via deletion tools, using a .NET tool interface.
An MCP server that provides tools for controlling Android devices using uiautomator2, enabling AI to automate tasks like tapping, swiping, and managing apps.
Enables Claude to send and read iMessages on macOS, with smart contact lookup, message history retrieval, and cross-conversation search using natural language commands.
Enables AI assistants to perform comprehensive Windows system health diagnostics, security checks, developer workflows, and maintenance tasks via 85 tools with actionable recommendations, over MCP and OpenAI-compatible HTTP.
Let an AI model use your PC: it reads each window as a numbered element list instead of screenshots, works in your open terminals, and pairs with phones and other PCs peer to peer using a 6-digit code. Bring any OpenAI-compatible model, including local ones.
Enables AI agents to search Apple devices, resolve hardware identifiers, check TSS signing status, download and verify official IPSW firmware images, inspect connected devices and backups, and generate validated restoration pipelines.
An MCP server that connects LLMs (Ollama, OpenAI, Anthropic) with desktop automation (mouse, keyboard, screenshots) using PyAutoGUI, with exclusive task locking to prevent concurrent execution.
An unofficial bridge that lets Claude Code control local macOS applications through an existing OpenAI Computer Use installation by launching the signed Codex client and translating MCP compatibility.
Enables users to record Windows desktop and browser workflows once and generate replayable Cursor Skills, using Playwright MCP and Windows Computer MCP for semantic, non-coordinate replay.
MCP server for organizing files on your Mac Desktop by automatically categorizing them into folders. Supports listing, previewing, and moving files into category folders (Images, Documents, Videos, etc.).
Enables AI agents to control and interact with a local Windows computer through authenticated MCP tools, including file operations, shell commands, process management, HTTP requests, and system/media inspection.
Lets MCP clients discover and run AppleScript or JavaScript for Automation (JXA) to control macOS applications, inspect the system, or reuse scripts from a bundled knowledge base.
Wraps the mcp-locks CLI to expose coordination primitives as MCP tools, enabling multiple AI agents to claim, release, and list exclusive OS resources like browser profiles.
Lets AI assistants understand what you're working on — current screen content, recent dictation, clipboard, and saved notes — running entirely on your own machine with nothing sent to the cloud.
A TypeScript-based server that enables programmatic management of pseudo-terminal sessions. It allows users to spawn, control, and interact with terminal processes in real-time through the Model Context Protocol.
Enables AI agents to inspect pending updates and service health for Proxmox VE VMs and containers, then take snapshots, apply official updates, reboot, and roll back under tag-based permissions and human-confirmed risky actions.
MCP server that reads and writes the system clipboard — tables, text, code, JSON, URLs, images, and more. Preserves spreadsheet structure (rows/columns) that is lost when pasting into Claude directly.
Enables MCP-speaking clients to control a real desktop via the computer_use tool, including clicking, typing, scrolling, dragging, key combos, app focus, and screen/accessibility capture. It also provides a verdict system that verifies whether input actions had their intended effect, with configurable approval modes.
Enables AI assistants to control mobile and desktop devices with natural language, including running automation tasks, taking screenshots, and managing devices.
Enables AI agents to capture and analyze screenshots of macOS applications, windows, or the entire screen using local (Ollama) or cloud-based AI vision models, with non-intrusive, fast screen capture via Apple's ScreenCaptureKit.
Enables communication between Claude Code sessions in iTerm2 panes, primarily for notifying other sessions when a PR is merged to main so they can pull latest changes.
Enables AI agents to inspect and control Java Swing and AWT desktop applications through the JVM's accessibility tree, including finding elements, clicking, typing, reading tables, and managing windows without modifying or injecting into the target process.