"How to run desktop commands on a computer" matching MCP servers:

Enables AI agents to interact with the Execute.run bot API for managing Shell balances, transferring funds, and executing LLM requests. It provides tools for identity verification, transaction tracking, and performing compute tasks through the Execute.run platform.

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

Enables you to audit your AI agent skills by running each one against an agent that cannot see it, diffing the resulting artifacts, and grading whether each skill genuinely improves, changes nothing, or worsens the output.

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.

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.

Enables secure execution of Python code in a sandboxed WebAssembly environment using Pyodide and Deno. Automatically handles package management and captures complete execution results including stdout, stderr, and return values.

Bridges the ChatGPT web UI to a local development environment over MCP, letting the model read and patch files, run real shell commands and terminals, execute tests, and control the desktop (screen, mouse, keyboard, clipboard) within user-approved folders. It adds parallel workers, goal/loop long-task control, plugin tools, and a security-hardening layer with risk-tiered shell policy, audit logging, and credential sanitization.

An MCP server that lets agents observe and control an Omarchy or Hyprland desktop: list monitors, windows, workspaces, and accessibility controls, capture screenshots, then move the pointer, type text, send shortcuts, and manage windows and workspaces. It works over stdio with any MCP client, guarding actions with session-lock and single-driver checks while treating on-screen content as untrusted data.

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.

A compact facade MCP server for macOS desktop automation, lazily proxying to full-featured computer-use tools to save context tokens while enabling screenshots, window control, app launching, and AppleScript execution.

Enables AI agents to call tools through a security gateway that intercepts requests, enforces deterministic policy and risk checks, blocks or escalates high-risk actions for human approval, and keeps tool credentials and audit logs protected.

A framework-agnostic computer-use MCP server that exposes core desktop operations (screen capture, mouse, keyboard, and file access) as standard MCP tools, enabling any MCP-compatible agent to drive a computer.

Enables AI agents to capture multi-monitor screenshots with coordinate grids and perform mouse, keyboard, scrolling, dragging, and window-management actions on Windows via MCP tools or CLI. It provides pixel-accurate desktop automation for computer-use agents.

Enables supervised, visible control of a Windows desktop from an MCP client, providing real mouse and keyboard input, screenshots, local safety controls, and a teaching mode for guidance without injection.

Provides a JSON-RPC computer use runtime for macOS, exposing 7 MCP tools (observe/act/inspect/session/cancel/trace) as image content blocks so external agents like Claude Code, Pi, OpenCode, or Codex CLI can capture screenshots and drive the desktop with clicks, keys, and typing while enforcing session locking, stale-frame protection, and trace redaction server-side.

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 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 agents to drive a Linux/X11 desktop via AT-SPI accessibility-tree perception and element-level actions, avoiding screenshots and coordinate clicking.

Windows desktop automation MCP server enabling screenshot capture, precise visual locating of UI elements via vision models, and automated mouse clicking.

Enables multiple local AI desktop applications to exchange MCP messages and collaborate through a shared JSONL room file, with role-based routing, history, and audit session tools.

Enables MCP clients to capture screenshots and control a Raspberry Pi's Wayland desktop over an existing SSH connection with mouse, drag, scroll, keyboard, and Unicode typing actions. Input tools return fresh screenshots, enforce single-client sessions with idle release, and reject stale or uncertain state until verified.

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.

Enables fast, precise control of web browsers and the physical desktop through MCP, combining DOM and native OS accessibility targeting with vision-based fallback and human-like mouse movement. Supports clicking, typing, scrolling, dragging, and drawing on canvas or paint applications across Linux, Windows, and macOS.

MCP server enabling AI agents to control a real Linux browser with live view, human takeover, and safety guardrails.

Open-source computer use MCP server for macOS and Windows, including remote Windows over SSH. Reads accessibility/UI Automation trees and uses Jev for element selection and action verification, with optional screenshot localization for icons and game scenes.

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.

Enables MCP clients to inspect and control an Omarchy/Hyprland desktop by taking screenshots, focusing windows, moving/clicking the mouse, scrolling, typing text, and sending keyboard shortcuts.

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 other agents to list, read, start, and steer Codex chats in the macOS ChatGPT desktop app, including sending follow-ups, choosing model/reasoning/speed, interrupting work, and answering approvals. It can run locally or behind bearer-token-protected tunnels for remote monitoring and control.

Enables Claude Code, Cursor, and Codex users to orchestrate plan/build/review workflows across host or CLI models with a spec gate, tool vetting, hard per-run and per-day cost/token limits, safe defaults, and clear logs.