- Conduid
- Marketplace
- #desktop-automation
MCP servers tagged desktop-automation
161 live MCP servers tagged "desktop-automation", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with desktop-automation.
Omp Cua
Low-overhead Cua Driver integration for Oh My Pi
Macos Computer Use Kit
AX-first computer use for AI agents on macOS with optional Jev (TypeSafe System One) semantic guards: calibrated target/input judgments before an irreversible action, decisions ke…
Computerpilot MCP
Cross-platform MCP runtime for supervised computer use and developer automation: files, terminal, code intelligence, browser/desktop control, durable jobs, recovery, and workflows.
Claude Codex Computer Use
Use an existing OpenAI Computer Use installation from Claude Code on macOS
Uitars MCP
Desktop + browser GUI agent MCP server. VLM-powered automation: screenshot → vision model → mouse/keyboard/Playwright actions. 9 MCP tools. Fits RTX 4090.
Desk MCP
Windows desktop automation MCP server - screenshots, OCR, mouse and keyboard, and accessibility trees via UI Automation, MSAA and Chrome DevTools Protocol. Node.js + built-in Powe…
Claude Codex Computer Use
Drive macOS apps from Claude Code through the Computer Use engine of OpenAI's ChatGPT/Codex app — no Codex quota, zero model turns per click: script (cua_repl-style JS), batch wit…
Silex
Desktop application for Silex, the free/libre no-code website builder. Built with Tauri v2 and the silex-server Rust crate.
Gramps AI Desktop Plugin
Gramps AI Desktop Plugin: 58 local tools for Gramps windows, native editors and database workflows; Codex, Claude Code, Kimi, Hermes, OpenCode and Grok via OpenCode.
Screen MCP
Linux Wayland computer-use MCP for Claude Code & Grok — screenshot, click, type any desktop app.
Iris MCP
High-precision Windows desktop control for AI agents via MCP. Three rendering backends (Win32 + UIA + OCR), Per-Monitor V2 DPI, SendInput + UIA Invoke clicks, live accuracy bench.
Extra
The Open-Source Astra 6 for your PC. Your AI can see, click, type, navigate, and get real work done on Windows.
AI Bridge
Reusable AI bridge for Laravel: multi-provider connectivity, chat streaming, knowledge/MCP server, and agent tools.
Lasso
Claude Code 的全交互对外抓手 MCP —— 搜/抓/登录态抓/控桌面(macOS·Win·Linux)，四通道+多引擎 fallback+cookie AES-256+markdown 抽取，一个 MCP 全包。 | All-in-one interaction MCP for Claude Code — search / scrape / l…
Xcomputer
AI-driven Windows desktop automation assistant — control your PC with natural language (like GitHub Copilot, but for desktop operations)
Sloth MCP
MCP server that lets Claude use your Mac — native apps and the browser — by remembering what it has seen instead of screenshotting every step.
ManuMCP
Cross-platform local MCP agent for ChatGPT, Codex, Claude Code, Gemini CLI and Cursor with whole-computer files, apps and desktop control.
Anode
Windows desktop automation for AI agents. MCP server and CLI with a background child session, screenshots, separate mouse/keyboard focus and app testing.
Web Agent
Local-first web & desktop automation toolkit: browser automation, video transcription, local OCR & VLM vision, desktop control — 数据全部本地处理，零上传
YourHand Community
YourHand Community — open-source, permission-aware Windows device control via MCP (source preview).
Tipray GreenShield Decryption Assistant
天锐绿盾（Tipray Green Shield）授权解密申请助手：Windows F8 快捷键 + 本机 MCP Server，支持文件/文件夹、官方审批链与 AI Agent 自动续跑。
Tato Runtime
The hands of an AI agent.
Opensource Everything
Study an existing product, turn it into build-ready artifacts, and verify your clone against the reference.
Dsh Plugin Computer Use
Safe Computer Use plugin for DeepSeek Harness with approvals and local audit archives
Deixion
C++23 Windows application automation for Claude Code via MCP: screenshots, Meridian coordinates, UI Automation, tray, hotkeys and bilingual UI.
Reflex Cu
Computer use MCP server for Claude Code, Codex and other AI agents. Reads the UI tree instead of taking a screenshot every step, with Jev (TypeSafe System One) as a fast judge. Lo…
ReMCP
only device agents.
Hands
给她一双手：把手机 App 里的人设接上电脑的 335 个 MCP 工具（能看图、能读屏幕）· One exe, 335 MCP tools for your phone-side persona (Windows, MIT)
Screen MCP
Linux Wayland computer-use MCP for Claude Code & Grok — screenshot, click, type any desktop app.
Macos Desktop Control
MCP Server for native macOS desktop automation. Screenshot, mouse, keyboard, window management. Works with Claude Code, Codex CLI, Gemini CLI, Cursor, and any MCP client.
Cua Desktop Operator Skill
MCP skill that lets any AI agent operate a Windows desktop — clone-ready, model-agnostic, no cloud required
Lazy Desktop MCP
Local-first desktop control MCP server with a Rust host and Node launcher.
Axterminator
MCP server for macOS desktop automation. Background GUI testing, 30 tools, audio capture, camera, virtual desktops. Built in Rust.
Electron Driver
MCP server that lets AI agents drive Electron apps — click, type, drag, screenshot, eval JS in the renderer or main process, capture console logs. 38 tools, Playwright-powered, wo…
Kimi Computer Use
Use an existing OpenAI Computer Use installation from Kimi Code CLI on macOS
Helix Pilot
GUI automation MCP server powered by local Vision LLM (Ollama). Control your Windows desktop from Claude Code, Codex CLI, and other MCP clients.
Agent Evidence MCP
面向 agent 长任务的本地 MCP，自动保存截图、短录屏、打码副本和可复盘证据。
Empir3 Bridge
Local-first MCP bridge — orchestrate the AI CLIs you already pay for (Claude, Codex, Gemini, Grok) and drive a real browser + desktop, all from one agent.
Winreach MCP
WinReach — give your AI agent its own Windows machine. Remote PowerShell, file transfer, screenshots, and full desktop control (computer use) over HTTP, secured with per-user keys…
Opencode Gui Bridge
A MCP bridge that gives AI assistants real Windows GUI control: UIA/OCR/CDP element snapshots, click/input/verify loop, occlusion-safe window capture.
Linux Desktop
MCP server for full Linux desktop control — windows, mouse, keyboard, clipboard, audio, screenshots, OCR, notifications, accessibility tree.
SoftAuto MCP
Open-source Windows RPA and MCP server for AI agents — UIA desktop automation, browser DOM automation, ERP workflows, and fast element-level execution beyond screenshot-by-screens…
Supergravity MCP
MCP server that lets Claude (or any MCP client) delegate tasks to Google's Antigravity desktop app. Built for Intel Macs Antigravity's own CLI doesn't support.
Screen Use
browser-use, but for the entire desktop — give any AI Agent eyes and hands on Windows. MCP + SDK, VLM-optional, with visual loop, introspection and meta-learning.
Blindpilot MCP
computer-use MCP server for non vision LLM models using accessibility trees and text-based interaction.
Microsoft Paint MCP Server
A semantic MCP interface for Microsoft Paint that lets AI work with geometry, diagrams and visual primitives instead of screen coordinates — powered by Windows UI Automation, Win3…
Dsh Nuphus MCP
DeepSeek Harness (DSH) plugin: mount the nuphus-mcp desktop automation MCP server as native tools (mcp__nuphus-mcp__*).
Ari VoiceCommand
Open-source Windows AI voice assistant and autonomous desktop agent built with Python/PySide6. Supports wake words, speech-to-text, text-to-speech, local LLMs with Ollama, MCP too…
Windows Computer Use Skill
Top-level Windows computer-use skill with a bundled standalone runtime and MCP server, zero local Claude dependency.
AI Hands
Multi-layer desktop automation for AI agents — browser CDP, Windows UIA, vision/OCR. Successor to AIWander/hands.