"How to operate a computer and execute commands" matching MCP servers:

An MCP server that lets you define and run custom shell commands via YAML templates, with built-in tools for flashing and serial communication in embedded development.

MCP server for executing shell commands with automatic RTK token reduction, persistent caching, and execution logging.

An MCP server to run commands.

An MCP server that adds a safety layer with eight independent checks and audit logging between a language model and a broker order, supporting both on-disk simulation and live MetaTrader 5 terminals.

Enables AI assistants to execute predefined developer commands and manage long-running processes through a JSON configuration file. Supports both one-shot commands and daemon processes with automatic process lifecycle management.

An open-source MCP server that lets any coding agent operate your computer like a person does—reading the UI through accessibility trees, clicking and typing in the background, showing an agent pointer, zooming into regions, and driving your signed-in Chrome on macOS, Windows, and Linux.

MCP server enabling Claude Code to capture screenshots of Windows applications through WSL2, allowing AI to diagnose UI errors and verify layouts.

MCP server for AI agents to control a Mac via screen and mouse/keyboard, supporting Anthropic Claude and OpenAI for task automation.

Enables local computer diagnostics by sampling CPU, memory, disk, and network activity and displaying the busiest processes in an interactive dashboard. It also supports human-confirmed process-stop proposals while keeping diagnostics local and bounded.

Gives AI agents controlled access to a computer for browsing, editing, searching, and organizing files; creating and extracting zips; running terminal commands; managing background processes; and transferring files. Supports automatic public tunnel access plus options to restrict folders, use read-only mode, disable the terminal, and expire download/upload links.

Enables AI agents to use a desktop computer with event-driven settling, waiting for the screen to react and stabilize before returning a settled screenshot and verdict.

Enables ChatGPT to read and edit local text files, apply precise string replacements, and run Bash commands on a user's own macOS or Linux machine through a secure local tunnel without exposing public ports.

Enables an agent to observe and operate desktop apps and browsers through an accessibility-tree-first view, with clicking, typing, scrolling, dragging and waiting tools. Screenshot handling, coordinate mapping and fail-closed safety rules (risk confirmation, deny-listed apps, stale-observation refusal) are enforced inside the server.

Enables an agent to see and operate a GNOME Wayland desktop like a human, including screenshots, mouse/keyboard control, accessibility tree access, OCR, clipboard, and audio listening.

MCP server for Windows computer use, providing low-token, low-latency automation through UIA/Win32, OCR, and vision. It enables batch actions, shortcuts, isolated desktop execution, and browser control via MCP tools.

Exposes Anthropic's computer-use action surface (screenshot, click, move, keyboard, clipboard, batch) against a persistent desktop display via MCP stdio protocol. Enables AI agents to control a virtual desktop environment through natural language instructions.

MCP server that enables Claude to control your computer, similar to Anthropic's computer use but easy to set up locally.

Enables AI agents to operate local desktops and Chromium browsers through MCP tools, unifying accessibility trees, physical input, screenshots, DOM/ARIA, visual grounding, and result verification.

Enables read-only inspection and diagnosis of Windows, macOS, and Linux machines through eight diagnostic tools covering system profiles, baselines, disk health, startup audits, driver context, and upgrade planning, with voice summaries and a web simulator. It enforces an R0-R3 risk model in code so only safe R0 evidence collection is automatic while riskier actions remain manual guidance.

Enables AI hosts to drive cross-platform desktop GUI automation and browser control, providing tools to read, click, type, send shortcuts, screenshot, and verify GUI elements and web pages.

Enables computer control via mouse, keyboard, OCR, and screen/window management, similar to Anthropic's computer-use.

Safety middleware for AI computer use agents that monitors, enforces policies, and provides guardrails to enable safe desktop interaction.

Gives each agent its own isolated nested Hyprland desktop with a private seat, clipboard and accessibility bus, so it can see the screen and drive a mouse, keyboard, touchpad gestures, windows and apps without touching the user's pointer, focus or windows. Exposes screenshots, zoom, OCR, accessibility-tree control, window management and batched actions as MCP tools, and can optionally act read-only, or with input, on the real desktop.

Enables a constrained subagent to perform foreground GUI actions on Hyprland—observing, focusing windows, clicking, typing, scrolling, dragging, and managing the clipboard—under per-action approval with lease, audit log, and kill-switch gating.

Enables MCP-capable AI agents to control Windows desktops through UI Automation element trees, native screenshots, app launching, batched action sequences, smart waits, and safety gates using normalized coordinates.

Enables models to remotely control computers over an MCP link, running commands, managing files, automating desktops and browsers, transferring data, and coordinating durable tasks across sessions.

Bridges Kimi Code CLI to OpenAI Computer Use, enabling Kimi to control local macOS applications via MCP.

Enables agents to discover and operate local macOS applications through ten Computer Use tools, including reading UI state and screenshots, clicking, typing, scrolling, and dragging, while requiring explicit human approval for new app access.

Gives a coding agent its own Docker-hosted Linux desktop with XFCE, Chromium, Blender, LibreOffice, GIMP and a sudo shell, exposing tools for screenshots, mouse and keyboard input, window focus, shell commands, file read/write, opening URLs or GUI apps, and headless Blender renders. The agent can watch and drive that desktop live from a browser while working on the shared project folder.

Enables window management, screenshot, typing, and clicking on X11 with multi-monitor support.