"Construct 3" matching MCP servers:

Enables voice-controlled hardware to execute approved Mac actions (like opening apps and querying system status) through a secure MCP bridge.

MCP server for building and driving VMware Workstation VMs from an AI agent, enabling unattended OS installs, guest command execution, file transfer, screenshots, and fleet management.

Enables LLMs to interact with Things 3 task manager on macOS via AppleScript, allowing users to list and create todos across different lists through natural language.

Enables management of system users through a simple sample API, exposed as MCP tools for natural-language interaction.

A personal desktop automation MCP server providing tools for screen/mouse/keyboard control, Windows UI automation, headless browser automation, file management, app execution, clipboard management, and a personal SQLite database for todos, notes, and habits.

Enables MCP-compatible clients to inspect the local machine's CPU, memory, and disk information through tools, a structured resource, and an upgrade-assessment prompt.

Provides agents with real Linux VMs to run commands, manage files, expose ports, and track costs, all through an ephemeral sandbox service.

Enables natural-language diagnosis of Linux system issues by providing sandboxed, typed tools for system, service, filesystem, and git inspection, with human approval for mutating actions.

Enables AI assistants to read, send, search, and manage emails in Apple Mail on macOS.

Enables the execution of AppleScript and JavaScript for Automation (JXA) on macOS to control applications, system events, and shell commands. It provides native automation capabilities with a security layer that permits most operations while specifically blocking file deletion commands.

A comprehensive MCP server for Frida dynamic instrumentation, enabling AI agents to manage devices, processes, scripts, memory, and ADB operations.

A Model Context Protocol (MCP) server that provides file deletion capabilities. This server allows AI assistants to safely delete files when needed, with support for both relative and absolute paths.

Empowers AI agents to see, reason, and control computers via VNC, providing advanced vision features like OCR and image search, human-like input control, and optional SSH remote command execution.

Enables AI agents to interact with IBM i systems through SQL tools and commands, supporting secure authentication, system monitoring, and database operations via the Model Context Protocol.

Enables agents to inspect Windows desktop UIs through compact UI Automation snapshots with stable element IDs and to execute batched mouse, keyboard, window, and wait/assert actions without relying on screenshot loops.

Enables AI agents to browse N-able N-central RMM data such as org unit hierarchies, devices, assets, lifecycle and service status, active issues, scheduled tasks, custom properties, maintenance windows and access groups. On explicit request it also performs writes — running scripts or automation policies on a device, changing custom properties or lifecycle data, adding or deleting maintenance windows, and creating device or org unit access groups.

Bridges AI assistants to Linux D-Bus for system interaction, enabling clipboard, notifications, screenshots, and service discovery with configurable security levels.

Provides native macOS desktop automation for AI agents, enabling screen capture, mouse/keyboard control, window management, and iOS/Android simulator control in both foreground and background modes without focus stealing.

Enables AI agents to inspect and drive native Windows desktop applications (WinForms, WPF, WinUI 3, and WebView2 hybrids) through Microsoft UI Automation by capturing interactive control snapshots, then clicking, filling, and asserting on elements via ephemeral refs or semantic screen-map targets. Mutating actions are dry-run by default and gated behind explicit arming, allow-lists, and a kill switch for lawful, assisted QA testing.

Native Windows MCP server that gives AI agents full desktop control. 45+ tools using UIAutomation + OCR with automatic dark theme enhancement instead of screenshots. Features batch action sequencing (run_sequence), window occlusion detection, menu navigation, PrintWindow capture, and embedded AI workflow instructions. Single .NET 8 executable — no Python, no Node, no Selenium.