MCP servers and skills: search, filter by where they run, and compare.
25–48 of 85 tools for “uia”
Clear allMCP server for Windows desktop computer use (mouse, keyboard, screenshot, OCR, window management)
GoApache-2.0★ 4Few starsNo key
Safe browser and Windows computer-use tools for OpenCode, exposed through MCP.
Node.jsMIT★ 1Few starsNo key
QCU (Quick Computer Use) — a faster computer-use skill that prefers the accessibility tree over screenshots. Web + macOS desktop automation.
SkillMIT★ 3Few starsNo key
Windows desktop automation via W3C WebDriver protocol — like ChromeDriver, but for Windows apps
SkillMIT★ 18No key
Open Source AI Design Architect that helps developers generate UI systems, design recommendations, components, color palettes, UX insights, and production-ready interfaces.
SkillMIT★ 6No key
OpenCode Computer Use: local Codex-style visual desktop control for Windows (MCP stdio, 35 tools, DPI-correct, verified E2E)
PythonMITFew starsNo key
Move things without touching them — an MCP server that lets AI agents see and control the desktop through platform accessibility APIs (AT-SPI, UIA, AXAPI).
SkillAGPL-3.0★ 3Few starsNo key
One vision layer for AI agents on Windows - a single MCP server to see and act on desktop apps, Electron windows, and the browser (undetected). Screen as structured text, so text-only LLMs work too.
PythonMITFew starsNo key
Screenshot and read on-screen UI elements/buttons with pixel coordinates (accessibility tree + OCR); optional click.
SkillMITFew starsNo key
跨框架 Agent Skills 合集：视频笔记生成、本地识图、Windows 桌面/浏览器自动化，外加 Hermes 语言路由插件。DSH 插件已拆分为独立仓库。
SkillMIT★ 6No key
A computer-use tool that exposes structured UI information and supports efficient multi-action execution.
SkillMIT★ 1Few starsNo key
Drive and inspect a whole Windows machine from Bun — apps, windows, input, screen, OCR, registry, and OS — exposed as a security-gated, profile-based MCP server. Pure TypeScript over bun:ffi, zero nat
Node.jsMIT★ 2Few starsNo key
Fully local desktop automation agent. Five OpenVINO INT4 agents see the screen, plan, act, and verify their own work. No cloud calls, no data leaves the machine.
SkillApache-2.0★ 1Few starsNo key
Blink：Windows 丝滑启动器，用搜索、Chord 和 AI 快速调用截图、翻译、语音、便签、剪贴板等本地能力。A smooth Windows launcher that uses search, Chord, and AI to quickly access local capabilities such as screenshots, translation, voice, note
SkillMIT★ 7No key
Semantic UI automation and lightweight accessibility snapshots for LLM agents to interact with Web and Desktop applications.
PythonMIT★ 32No key
AI-driven WPF UI testing agent integrated with Claude Code. Claude reads screenshots, understands UI state, and autonomously explores and tests your application — then fixes issues it finds.
SkillMIT★ 2Few starsNo key
High-performance Rust MCP server for Windows desktop automation, native accessibility tree navigation, and system-level LLM orchestration.
SkillMITFew starsNo key
DSH / DeepSeek Harness 的 Windows 电脑控制插件：截图、识别控件、点击、中文输入、OCR 和 Esc 急停。C# + TypeScript computer-use plugin.
SkillMIT★ 1Few starsNo key
WinCode is a Windows/.NET MCP assistant for background UI inspection and code intelligence. It reduces screenshot-driven computer-use overhead with structured controls, runtime states, and source evid
SkillMIT★ 1Few starsNo key
MCP server for Windows desktop automation (FlaUI + UIA) - Claude Code plugin install, ARM64 builds, stability fixes over upstream
SkillMIT★ 3Few starsNo key
MCP server giving an MCP client hands-on control of a Windows desktop: windows, input, screen capture, UI Automation, processes, registry, services, files, clipboard.
SkillMIT★ 3Few starsNo key
Windows port of typesafe-computer-use with Jev decisions, local OCR/UIA, and MCP host integration
SkillMIT★ 5No key
AI-native testability, automation and evidence-based verification toolkit for Makepad applications.
SkillMIT★ 1Few starsNo key
Local Windows control for Codex: webpage elements, desktop controls, screenshots and mouse/keyboard input. Optional Jev.
SkillMIT★ 2Few starsNo key
Who stands behind it
