Potencia tu agente
El comando propio del publicador. No es un endpoint de PlugMCP.
Host a copy with our keys and logs.
npx -y @harusame64/[email protected]Claude Code no tiene enlace de instalación para un comando local. Copia el comando de abajo y ejecútalo en una terminal.
claude mcp add harusame64-desktop-touch-mcp -- npx -y @harusame64/desktop-touch-mcp@2.4.3Ejecútalo en una terminal.
{ "mcpServers": { "harusame64-desktop-touch-mcp": { "command": "npx", "args": [ "-y", "@harusame64/[email protected]" ] } }}claude_desktop_config.json
¿URL remota o un comando en tu máquina? En qué se diferencian las dos instalaciones
Ejecutar en PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
AbrirDel publicador
Let Claude, Cursor, or any MCP client see and operate your Windows 10/11 desktop. 32 tools for screenshots, UI Automation, Chrome CDP, keyboard/mouse, terminal, with semantic discover-then-act targeting and per-action perception guards that avoid wrong-wi
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_discoverreturns interactive entities with short-lived leases instead of raw coordinates, sodesktop_actoperates 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_actalso 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 byhwndreaches that window only. See the CHANGELOG.
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).hwnd never lands in another window with the same title.desktop_discover and screenshot(detail="text") switch to a Hybrid Non-CDP pipeline — Rust-powered grayscale + bilinear upscale → Windows OCR → clustering → red bounding boxes with numbered badges ([1], [2]…). Two representations come back: a PNG for spatial orientation and an elements[] list with clickAt coords — no CDP required.ssh / sudo in a console opened by key_locker(action='launch_console') — the password is filled in automatically when the hidden prompt appears, with a per-fill confirmation prompt by default. See Key Locker.napi-rs + windows-rs): UIA is called over COM from a dedicated thread instead of spawning PowerShell, and image diffs use SSE2 SIMD. Without the addon, every function falls back to PowerShell transparently. The npm launcher fetches only the GitHub Release matching its version and verifies the Windows runtime zip before extracting it.run_macro batches multiple operations into a single API call; diffMode sends only the windows that changed since the last frame. Minimal tokens, minimal round-trips.lensId for a window or browser tab, pass it to action tools, and get guard-checked post.perception feedback after each action. It reduces repeated screenshot / desktop_state calls and prevents wrong-window typing or stale-coordinate clicks.GetWindowTextW for window titles, avoiding nut-js garbling. IME bypass input supported for Japanese/Chinese/Korean environments.detail="image" (~443 tok) / detail="text" (~100–300 tok) / diffMode=true (~160 tok). Send pixels only when you actually need to see them.dotByDot=true captures at native resolution (WebP). Image pixel = screen coordinate — no scale math needed. With origin+scale passed to mouse_click, the server converts coords for you — eliminating off-by-one / scale bugs.grayscale=true (~50% size), dotByDotMaxDimension=1280 (auto-scaled with coord preservation), and windowTitle + region sub-crops help exclude browser chrome and other irrelevant pixels. Typical reduction for heavy captures: 50–70%.detail="text" on Chrome/Edge/Brave auto-skips UIA (prohibitively slow there) and runs Windows OCR. hints.chromiumGuard + hints.ocrFallbackFired flag the path taken.detail="text" returns button names and clickAt coords as JSON. Claude can click the right element without ever looking at a screenshot.window_dock(action='dock') snaps any window to a screen corner with always-on-top. Set DESKTOP_TOUCH_DOCK_TITLE='@parent' to auto-dock the terminal hosting Claude on MCP startup — the process-tree walker finds the right window regardless of title.Note: nut-js native bindings require the Visual C++ Redistributable. Download from Microsoft if not already installed.
Note (Key Locker): The credential helper Key Locker uses is an unsigned executable, so on some machines Windows SmartScreen or antivirus may show an "unknown publisher" warning the first time it runs. This is expected — the helper ships with desktop-touch-mcp and runs locally on your machine; you can allow it to proceed. Code signing is planned for a future release.
npx -y @harusame64/desktop-touch-mcp
The npm launcher resolves runtime strictly by npm package version. For package X.Y.Z, it fetches only GitHub Release tag vX.Y.Z, downloads the zip for your platform (desktop-touch-mcp-windows.zip, or desktop-touch-mcp-macos-arm64.zip on an Apple Silicon Mac), verifies its SHA256 digest, and only then expands it under %USERPROFILE%\.desktop-touch-mcp (~/.desktop-touch-mcp on macOS). Verified cached releases are reused on later runs.
Set DESKTOP_TOUCH_MCP_HOME to override the cache root directory.
Old releases are removed once the server has started, keeping the one being run and one other (about 180 MB each on Windows). Set DESKTOP_TOUCH_MCP_KEEP_RELEASES to keep more (0 keeps all). A release another client is running is kept. Removing an old releases/vX.Y.Z folder by hand is also safe while no client runs it.
On a shared or CI network? The first run reads the GitHub Releases API to locate the runtime zip. The anonymous limit is 60 requests/hour per IP, which a shared public address (CI runners, office NAT) can exhaust before your download even starts. Set
GITHUB_TOKEN(orGH_TOKEN) in the environment and the launcher authenticates the request, raising the limit to 5,000 requests/hour. No token is needed on an ordinary home connection.
Running the launcher from a source checkout? A source build's
bin/launcher.jscarries a placeholder integrity hash (sha256: "PENDING") instead of a finalized one. Rather than download and run an unverified runtime, the launcher fails closed — this guard stops an accidentally published or unfinalized launcher from silently starting unverified code. Published npm releases always ship a real SHA256, so end users never see this. If you are intentionally running the launcher from source, setDESKTOP_TOUCH_MCP_ALLOW_UNVERIFIED=1to skip integrity verification (development only).
Does your host give up before the launcher finishes? Some desktop hosts allow a plugin a fixed budget — 60 seconds is common — to become ready, and a launcher waiting on an unreachable GitHub can spend all of it. Two environment variables cover that case.
DESKTOP_TOUCH_MCP_FETCH_TIMEOUT_MS(default15000) bounds how long the launcher waits without hearing from GitHub. It applies to the release lookup and to the download; for the download it counts silence rather than total time, so a large runtime still installs over a slow connection. A value that is not a positive number of milliseconds is ignored with a warning.
DESKTOP_TOUCH_MCP_OFFLINE_FALLBACK=1lets the launcher start a release that is already installed when GitHub cannot be reached at all. It is off by default. GitHub is always contacted first, so a reachable network still re-downloads and repairs a damaged install; only a network failure reaches the fallback, which starts the copy of your version on disk — without re-verification — or, when that version was never installed, the newest older release that completed a verified install. Answers that are not network failures (a 404, the API rate limit, a mismatched integrity hash) still stop startup loudly. Leave it off unless a host timeout forces your hand: while it is set, a corrupted install of your current version is reused instead of being repaired.The two work together: with the fallback on, startup still waits out the timeout before falling back, so lower
DESKTOP_TOUCH_MCP_FETCH_TIMEOUT_MSif your host's budget is tight. Note also that a download which is still arriving, however slowly, is never interrupted — the fallback answers when the network has gone silent, not when it is merely slow.
Add to ~/.claude.json under mcpServers:
{
"mcpServers": {
"desktop-touch": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@harusame64/desktop-touch-mcp"]
}
}
}
No system prompt needed. The command reference is automatically injected into Claude via the MCP initialize response's instructions field.
Clients that require an HTTP endpoint (GPT Desktop, VS Code Copilot, Cursor, etc.) can use the built-in Streamable HTTP transport:
npx -y @harusame64/desktop-touch-mcp --http
# or with a custom port:
npx -y @harusame64/desktop-touch-mcp --http --port 8080
The server starts at http://127.0.0.1:23847/mcp (localhost only). Register the URL in your MCP client settings. A health check is available at http://127.0.0.1:<port>/health.
In HTTP mode the system tray icon shows the active URL and provides quick-copy and open-in-browser shortcuts.
git clone https://github.com/Harusame64/desktop-touch-mcp.git
cd desktop-touch-mcp
npm install
Build after install:
npm run build
For a local checkout, register the built server directly:
{
"mcpServers": {
"desktop-touch": {
"type": "stdio",
"command": "node",
"args": ["D:/path/to/desktop-touch-mcp/dist/index.js"]
}
}
}
Note: Replace
D:/path/to/desktop-touch-mcpwith the actual path where you cloned this repository.
Limited preview. The macOS build has only 4 of the tools — a small subset of the Windows build — and its behaviour may change between releases.
On an Apple Silicon Mac (macOS 14 or later) the same npx command starts a macOS server with four tools: desktop_state, desktop_discover, desktop_act (press, replace or append text) and screenshot (one window). The other tools are Windows-only and are not listed on macOS.
open "x-apple.systempreferences:com.apple.preference.security?Privacy_Accessibility"
open "x-apple.systempreferences:com.apple.preference.security?Privacy_ScreenCapture"
Then restart the MCP server — restart or reconnect it in your client, or restart the app that runs it: a server that was already running did not see a new Accessibility grant. If screenshots still fail after granting Screen Recording, quit and reopen that app. Until then the tools answer PermissionRequired and say what to grant.npx only: a release zip downloaded with a browser is refused by Gatekeeper (the native module is not notarized).--http is not available yet). Intel Macs and Linux are not supported.📖 Full Reference:
docs/system-overview.md— Exhaustive guide on parameters, return schemas, and coordinate math.
The v2 World-Graph surface (desktop_discover / desktop_act) is the recommended dispatch path. The four-call shape works for native apps, browsers, and terminals identically.
desktop_state → orient: focused window/element, modal, attention signal
desktop_discover → find actionable entities (returns lease + windows[])
desktop_act(lease, …) → act on entity (returns attention + post.perception)
desktop_state → confirm the world changed as expected
Clicking — priority order:
browser_click(selector) → Chrome / Edge (CDP, stable across repaints)
desktop_act(lease, action='click') → native / dialog / visual (entity-based; use after desktop_discover)
click_element(name | automationId) → native UIA fallback if desktop_act returns ok:false (not for list/tree/grid items)
mouse_click(x, y, origin?, scale?) → pixel last resort; origin+scale from dotByDot screenshots only
Recovery hints for each refusal, and how leases expire: Guide → Recovery hints and leases.
The details live in the guide:
until)screenshot key parametersHuge thanks to everyone who tried a desktop-automation MCP server, filed issues, opened PRs, and shared what broke. Every bug report made the next release better. Thank you for building with me!
MIT
Let Claude, Cursor, or any MCP client see and operate your Windows 10/11 desktop. 32 tools for screenshots, UI Automation, Chrome CDP, keyboard/mouse, terminal, with semantic discover-then-act targeti
{ "mcpServers": { "harusame64-desktop-touch-mcp": { "command": "npx", "args": [ "-y", "@harusame64/[email protected]" ] } }}Resumen general
Let Claude, Cursor, or any MCP client see and operate your Windows 10/11 desktop. 32 tools for screenshots, UI Automation, Chrome CDP, keyboard/mouse, terminal, with semantic discover-then-act targeting and per-action perception guards that avoid wrong-wi
Herramientas
Aún no hay lista de herramientas. Los servidores remotos la reciben tras la primera comprobación de estado.
Preguntas frecuentes
Copia en esta página la configuración stdio para Cursor, Claude Desktop, Claude Code o VS Code. Usa la instalación del publicador, no un proxy de PlugMCP.
Este registro no indica ninguna variable de entorno obligatoria.
@harusame64/desktop Touch se ejecuta localmente por stdio.
Última comprobación: 2026-11-16. Let Claude, Cursor, or any MCP client see and operate your Windows 10/11 desktop. 32 tools for screenshots, UI Automation, Chrome CDP, keyboard/mouse, terminal, with semantic discover-then-act targeting and per-action perception guards that avoid wrong-wi