제품 정보

Windows용 컴퓨터용 MCP 서버. Claude, Cursor, 또는 MCP 클라이언트가 Windows 10/11 데스크탑 - 스크린 샷, UI 자동화, 크롬 CDP, 키보드 / 마우스, 터미널 -semantic discover-then-act targeting를 사용하여 픽셀 좌표 추측 및 per-action perception guard를 방지합니다.

32 도구, 기본 Rust 엔진 (UIA 2 ms), 0 구성 PowerShell fallback, 전체 CJK 지원, MIT 라이센스. Claude / Cursor / VS Code Copilot config 및 Claude에 위의 스니펫을 추가하면 Notepad, Excel, Chrome, Windows Terminal 및 기계에 다른 응용 프로그램을 구동 할 수 있습니다.

이 픽셀 클릭 이상? 두 가지 아이디어는 모든 도구를 통해 실행됩니다. discover-then-act — desktop_discover]는 원시 좌표 대신 짧은 라이브 임대와 대화 형 엔티티티를 반환하므로 desktop_act는 whatwhat, not where it was — and per-action perception guards 입력 토지 전에 대상 창의 신원과 경계를 확인하고 잘못된 윈도우 타이핑 및 stale-coordinate click before they result. · **2.

desktop-touch-mcp

日本語

Computer-use MCP server for Windows. Lets Claude, Cursor, or any MCP client see and operate your Windows 10/11 desktop — screenshots, UI Automation, Chrome CDP, keyboard / mouse, terminal — with semantic discover-then-act targeting that avoids pixel-coordinate guessing, and per-action perception guards that catch wrong-window typing before it happens.

npx -y @harusame64/desktop-touch-mcp

32 tools, native Rust engine (UIA in 2 ms), zero-config PowerShell fallback, full CJK support, MIT licensed. Add the snippet above to your Claude / Cursor / VS Code Copilot config and Claude can drive Notepad, Excel, Chrome, Windows Terminal, and any other app on your machine.

Why this over pixel-clicking? Two ideas run through every tool: discover-then-act — desktop_discover returns interactive entities with short-lived leases instead of raw coordinates, so desktop_act operates on what you mean, not where it was — and per-action perception guards that verify the target window’s identity and bounds before input lands, catching wrong-window typing and stale-coordinate clicks before they happen.

2.1 reads UI Automation by element count instead of depth: Chrome, Edge and VS Code pages, Explorer and Settings values, and Word’s body are read and can be acted on, and what UIA still cannot see falls back to OCR and Set-of-Marks as before. desktop_act also types into Word’s body, and into Windows Terminal after asking the user. 2.0 refuses an action that cannot be done, with a reason, instead of reporting it done, and an action aimed by hwnd reaches that window only. See the CHANGELOG.

---

Features

• 🔁 Every act reports what it did — desktop_act answers with what changed: elements that appeared or disappeared, a modal, a focus move, the screen’s repaint (observation), and with narrate:"rich" the values and names that changed. The agent reads the result of its click from the reply instead of taking another screenshot. On UIA-blind targets it can also attach a PNG of just the region that changed (roiCapture; on by default for a visible change, returnCapture:"never" to suppress, "always" to force).
• 🛑 An act that cannot be done is refused, not reported as done — input that would not reach the field, a window blocked by a dialog, a closed window, a window on another virtual desktop: nothing is sent, and the reply names the reason and what to do next. An act aimed by hwnd never lands in another window with the same title.