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

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.

MCP server for controlling a transparent sci-fi cockpit overlay on your desktop, allowing AI agents to spawn, move, configure, and close holographic widgets (clock, system stats, map, etc.) via MCP.

Enables AI clients to control the Windows NetEase Cloud Music desktop app via local stdio MCP, including reading current song and liked state, searching and playing tracks, playback control, track skipping, and setting the current song's liked status.

Enables AI assistants to read and send WhatsApp messages on Windows through the official WhatsApp Desktop application using Edge WebView2 CDP automation.

Windows desktop automation MCP server — screenshot, mouse, keyboard & UI Automation. Lets LLM agents see and control your Windows desktop directly.

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 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.

an open-source MCP server that lets Claude Code (or Cursor, Codex, Gemini CLI) work inside the Notion Desktop app you’re already logged in to. No Company Authorise

An MCP server that provides Claude with comprehensive desktop automation capabilities including browser control, window management, and native mouse/keyboard input on Windows. It enables users to capture screenshots, launch applications, and interact with the system clipboard through natural language.

Exposes your project's package.json scripts as MCP tools, allowing AI assistants to discover and execute npm/yarn/pnpm/bun scripts directly. Automatically detects your package manager and enables running scripts with optional arguments through natural language commands.

GNOME desktop automation for AI agents. 30 tools via D-Bus: screenshots, window management, mouse/keyboard injection, clipboard, workspaces, and system notifications. Works on any GNOME 45–49 Linux desktop.

Enables comprehensive Trello integration through Claude Desktop, allowing users to search, create, update, and manage Trello boards, cards, lists, comments, and collaborate with team members through natural language.

Enables Codex to drive a locally running Windows Doubao desktop app over localhost CDP, so users can send tasks and follow-ups to existing conversations, wait for runs to finish, and read back replies. It also lists local sessions and checks connection status, without needing Doubao Web or an Ark API key.

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.

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.

Enables Claude Code to send prompts to Claude Desktop using macOS automation and AppleScript. Supports conversation management and configurable response polling, though reading responses back is limited by Electron's accessibility APIs.

A desktop MCP service that integrates voice assistants into Mac workflows, enabling Obsidian memory, app control, Claude Code sessions, pending actions, and multi-language HTTP access.

MCP server that fixes Windows DPI coordinate scaling for AI desktop automation. Provides UI element finding via Windows Accessibility APIs and coordinate conversion between physical and logical coordinate systems.

Enables safe Windows desktop automation and computer use through natural language, including window observation, UI Automation, and execution of verified actions like clicking, typing, and scrolling.

A production-oriented MCP server that exposes task-level WeChat Desktop automation to AI clients, enabling status checks, message fetching/reply, contact addition, and Moment publishing on macOS via accessibility automation.

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

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 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.

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.

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 tools to read and send messages through LINE Desktop via MCP, supporting manual or automatic sending without official LINE API tokens.

Enables agents to observe and operate macOS desktop apps, including existing browser windows and signed-in sessions, through a local MCP adapter.

Enables AI agents to observe and operate real desktops, mobile devices, and browser pages through screenshots, native accessibility trees, and web automation, including clicking, typing, hotkeys, and UI lookup across macOS, Linux, Windows, Android, and iOS.

Lets an MCP client see and control apps on a local X11 Linux desktop by clicking, typing, scrolling, dragging, and pasting text, with a visible Stop control that returns input to the user.