desktop-automation MCP servers & tools

Desktop GUI automation using accessibility APIs. Control Windows, macOS, and Linux applications without vision models or screenshots. Supports workflow recording, structured data extraction, and browser DOM inspection.

Desktop GUI automation on Windows, macOS and Linux via accessibility APIs instead of screenshots, plus workflow recording, data extraction and DOM inspection.

Safe cross-OS desktop control for any AI agent - the fallback execution layer.

An MCP Server for computer-use in Windows OS

Accessibility-first desktop control for any agent: background input, agent pointer, zoom, Chrome.

Accessibility-first desktop control for any agent: background input, agent pointer, zoom, Chrome.

Mac window manager your AI agent can drive: layouts, workspaces, snap zones, screenshots.

MCP server for desktop, browser (CDP), and Android automation. Screenshot, OCR, click, type.

Open-source computer use for macOS agents.

Model-agnostic computer-use MCP: screenshot, safety-gated actions, Windows UIA targeting.

Drive a running Ikenga desktop app from MCP clients — DOM, click, type, navigate, screenshot.

Playwright for the entire OS. Gives AI agents the ability to see, find, and interact with UI elements in any desktop application.

Control Windows desktop via MCP: mouse, keyboard, screenshots, clipboard, and apps.

MCP server for Elgato Stream Deck control — set buttons, manage pages, wire actions

⃣ 🏠 🪟 - Inspect, debug and drive running WPF (.NET desktop) apps: visual tree, dependency properties, data bindings and binding errors, DataContext, and screenshots with open popups/menus included, plus clicking, item selection, text input and keyboard shortcuts. Auto-injects into any running WPF process (x64/x86) with no source changes. dotnet tool install -g WpfVisualTreeMcp

Eyes and hands on real Windows PCs — observe, click, type via Glasswarp API.

Raycast workflow automation MCP server with 9 tools

Windows desktop automation that re-reads only what changed: 7x fewer tokens per task.

Windows UI Automation MCP server for desktop inspection and element lookup. Windows only.

Windows screen capture MCP server with display, region, and active-window capture tools.

MCP server for inspecting and automating Java Swing applications.

Instant, resettable Windows and Ubuntu desktop VMs for AI agents on Apple Silicon Macs.

Drive macOS apps without taking the cursor: read, click, type, scroll, each with evidence.

Let any AI agent operate desktop apps on macOS, Windows and Linux, in the background and safely.

Autonomous job application copilot, ATS form filler, and AI mock interview engine.

Secure Linux desktop automation - input, screen/OCR/vision, AT-SPI2 UI tree, window, clipboard

Drive a running Ikenga desktop app from MCP clients — DOM, click, type, navigate, screenshot.

Windows desktop control for AI agents: screen, UI Automation, input, processes, files, shell.

Real Linux and Windows desktop VMs for AI agents: exec, files, computer-use and snapshots via MCP.

Inspect and drive Avalonia, WPF and MAUI desktop applications through local MCP.

Local macOS 27 desktop automation through MCP on Apple silicon.