desktop-touch-mcp

日本語

Stop pasting screenshots. Let Claude see and control your desktop directly.

An MCP server that gives Claude eyes and hands on Windows — 57 tools covering screenshots, mouse, keyboard, Windows UI Automation, Chrome DevTools Protocol, clipboard, desktop notifications, SmartScroll, and a Reactive Perception Graph for safe multi-step automation, designed from the ground up for LLM efficiency.

v0.15: 82× average speedup via Rust native engine — UIA focus queries in 2 ms, SSE2-accelerated image diffing at 13–15× native speed. Zero-config: the engine auto-loads when present, with transparent PowerShell fallback. v0.15.5: Pinned release verification — the npm launcher now fetches only the matching GitHub Release tag and verifies the Windows runtime zip before extraction.

Features

• ⚡ High-performance Rust Native Core — The UIA bridge and image-diff engine are written in Rust (napi-rs + windows-rs) and loaded as a native .node addon. Direct COM calls from a dedicated MTA thread eliminate PowerShell process spawning — getFocusedElement completes in 2 ms (160× faster), and getUiElements returns full trees in ~100 ms with a batch BFS algorithm that minimizes cross-process RPC. Image-diff operations use SSE2 SIMD for 13–15× throughput. When the native engine is unavailable, every function transparently falls back to PowerShell — zero config required.

• 🎯 Set-of-Marks (SoM) visual fallback — Games, RDP sessions, and non-accessible Electron apps return clickable elements even when UIA is completely blind. screenshot(detail="text") automatically detects UIA sparsity and activates a Hybrid Non-CDP pipeline: Rust-powered grayscale + bilinear upscale → Windows OCR → clustering → red bounding-box annotation with numbered badges ([1], [2]…). Two parallel representations returned: a visual PNG for spatial orientation and a semantic elements[] list with clickAt coords — no CDP required.

• LLM-native design — Built around how LLMs think, not how humans click. 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.

• Reactive Perception Graph — Register a 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 / get_context calls and prevents wrong-window typing or stale-coordinate clicks.

• Full CJK support — Uses Win32 GetWindowTextW for window titles, avoiding nut-js garbling. IME bypass input supported for Japanese/Chinese/Korean environments.

• 3-tier token reduction — detail="image" (~443 tok) / detail="text" (~100–300 tok) / diffMode=true (~160 tok). Send pixels only when you actually need to see them.

• 1:1 coordinate mode — 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.

• Browser capture data reduction — 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%.

• Chromium smart fallback — detail="text" on Chrome/Edge/Brave auto-skips UIA (prohibitively slow there) and runs Windows OCR. hints.chromiumGuard + hints.ocrFallbackFired flag the path taken.

• UIA element extraction — detail="text" returns button names and clickAt coords as JSON. Claude can click the right element without ever looking at a screenshot.

• Auto-dock CLI — dock_window 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.

• Emergency stop (Failsafe) — Move the mouse to the top-left corner (within 10px of 0,0) to immediately terminate the MCP server.

Requirements

Note: nut-js native bindings require the Visual C++ Redistributable. Download from Microsoft if not already installed.

Installation

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 desktop-touch-mcp-windows.zip, verifies its SHA256 digest, and only then expands it under %USERPROFILE%\.desktop-touch-mcp. Verified cached releases are reused on later runs.

Set DESKTOP_TOUCH_MCP_HOME to override the cache root directory.

Register with Claude CLI

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.

Register with other clients (HTTP mode)

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.

Development install

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-mcp with the actual path where you cloned this repository.

Tools (57 total)

📖 Full command reference: docs/system-overview.md — every tool's parameters, response shape, coordinate math, layer-buffer strategy, and engineering notes in one place.

Screenshot (5)

Window management (4)

Mouse (5)

Keyboard (2)

UI Automation (4)

Browser CDP (12)

All browser_* tools that touch the DOM accept includeContext:false to omit the trailing activeTab: / readyState: lines (saves ~150 tok/call on chained invocations). Within a 500 ms window, consecutive calls reuse one tab-context fetch automatically.

Workspace (2)

Context / Wait / History (8)

Terminal (2)

Pin / Macro (3)

Clipboard (2)

Notification (1)

Scroll (2)

Browser CDP automation

For web automation, connect Chrome or Edge with the remote debugging port enabled — no Selenium or Playwright needed.

# Launch Chrome in CDP mode
chrome.exe --remote-debugging-port=9222 --user-data-dir=C:\tmp\cdp

browser_launch()                        → launch Chrome/Edge/Brave in debug mode (idempotent)
browser_connect()                       → list open tabs + get tabIds
browser_find_element("#submit")         → CSS selector → physical screen coords
browser_click_element("#submit")        → find + click in one step (auto-focuses browser)
browser_eval("document.title")          → evaluate JS, returns result
browser_fill_input("#email", "user@example.com") → fill React/Vue/Svelte controlled input (state-safe)
browser_get_dom("#main", maxLength=5000)→ outerHTML, truncated to maxLength chars
browser_get_interactive()               → links/buttons/inputs + ARIA toggles + viewportPosition per element
browser_get_app_state()                 → one-shot SPA state (Next/Nuxt/Remix/Apollo/GitHub react-app/Redux SSR)
browser_search(by="text", pattern="...")→ grep DOM with confidence ranking
browser_navigate("https://example.com") → navigate via CDP (no address bar interaction)
browser_disconnect()                    → clean up WebSocket sessions

For chained calls in the same tab, pass includeContext:false to omit the activeTab/readyState annotation (~150 tok/call saved). Boolean / object params accept the LLM-friendly string spellings ("true", "{}").

Coordinates returned by browser_find_element account for the browser chrome (tab strip + address bar height) and devicePixelRatio, so they can be passed directly to mouse_click without any scaling.

Recommended web workflow:

browser_connect() → browser_get_dom() → browser_find_element(selector) → browser_click_element(selector)

Auto-dock CLI on startup

Keep Claude CLI visible while operating other apps full-screen. Set env vars in your MCP config and the docked window auto-snaps into place every MCP startup.

{
  "mcpServers": {
    "desktop-touch": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@harusame64/desktop-touch-mcp"],
      "env": {
        "DESKTOP_TOUCH_DOCK_TITLE": "@parent",
        "DESKTOP_TOUCH_DOCK_CORNER": "bottom-right",
        "DESKTOP_TOUCH_DOCK_WIDTH": "480",
        "DESKTOP_TOUCH_DOCK_HEIGHT": "360",
        "DESKTOP_TOUCH_DOCK_PIN": "true"
      }
    }
  }
}

Input routing gotcha: when a pinned window is active (e.g. Claude CLI), keyboard_type / keyboard_press send keys to it, not the app you wanted to type into. Always call focus_window(title=...) before keyboard operations, then verify isActive=true via screenshot(detail='meta').

Reactive Perception Graph (4)

Reactive Perception Graph is desktop-touch's low-cost situational awareness layer. It keeps the target identity, focus, rect, readiness, and guard state alive across actions so Claude does not need to re-check everything with a screenshot after every small move.

# Register a lens on the target window or browser tab
perception_register({name:"editor", target:{kind:"window", match:{titleIncludes:"Notepad"}}})
→ {lensId:"perc-1", ...}

# Pass lensId to action tools. Guards run before the action;
# compact feedback arrives in post.perception after the action.
keyboard_type({text:"hello", windowTitle:"Notepad", lensId:"perc-1"})
→ post.perception: {attention:"ok", guards:{...}, latest:{target:{title, rect, foreground}}}

# If the app restarts or focus moves away, guards fail closed before unsafe input:
keyboard_type({text:"x", lensId:"perc-1"})
→ {ok:false, code:"GuardFailed", suggest:["Re-register lens for the new process instance"]}

lensId is opt-in on all action tools (keyboard_type, keyboard_press, mouse_click, mouse_drag, click_element, set_element_value, browser_click_element, browser_navigate, browser_eval). Omitting lensId preserves existing behavior exactly.

Mouse homing correction

When Claude calls screenshot(detail='text') to read coordinates and then mouse_click seconds later, the target window may have moved. The homing system corrects this automatically.

# Tier 1 only (automatic)
mouse_click(x=500, y=300)

# Tier 1 + 2: also bring window to front if hidden
mouse_click(x=500, y=300, windowTitle="Notepad")

# Tier 1 + 2 + 3: also re-query UIA if window resized
mouse_click(x=500, y=300, windowTitle="Notepad", elementName="Save")

# Traction control OFF — no correction
mouse_click(x=500, y=300, homing=false)

The homing parameter is available on mouse_click, mouse_move, mouse_drag, and scroll. The cache is updated automatically on every screenshot(), get_windows(), focus_window(), and workspace_snapshot() call.

mouse_click image-local coords (origin + scale)

When you take a dotByDot screenshot with dotByDotMaxDimension, the response prints the origin and scale values. Instead of computing screen coords manually, copy them into mouse_click:

# Screenshot response:
#   origin: (0, 120) | scale: 0.6667
#   To click image pixel (ix, iy): mouse_click(x=ix, y=iy, origin={x:0, y:120}, scale=0.6667)

mouse_click(x=640, y=300, origin={x:0, y:120}, scale=0.6667, windowTitle="Chrome")
# Server converts: screen = (0 + 640/0.6667, 120 + 300/0.6667) = (960, 570)

This eliminates a whole class of off-by-one and scale bugs. Without origin/scale, x/y remain absolute screen pixels (unchanged behavior).

screenshot key parameters

detail="image"          — PNG/WebP pixels (default)
detail="text"           — UIA element JSON + clickAt coords (no image, ~100–300 tok)
detail="meta"           — Title + region only (cheapest, ~20 tok/window)
dotByDot=true           — 1:1 WebP; image_px + origin = screen_px
dotByDotMaxDimension=N  — cap longest edge (response includes scale for coord math)
grayscale=true          — ~50% smaller for text-heavy captures (code/AWS console)
region={x,y,w,h}        — with windowTitle: window-local coords (exclude browser chrome)
                          without: virtual screen coords
diffMode=true           — I-frame first call, P-frame (changed windows only) after (~160 tok)
ocrFallback="auto"      — detail='text' auto-fires Windows OCR on uiaSparse or empty

Recommended Chrome combo (50–70% data reduction):

screenshot(windowTitle="Chrome",
           dotByDot=true, dotByDotMaxDimension=1280, grayscale=true,
           region={x:0, y:120, width:1920, height:900})  # skip browser chrome

Recommended workflow:

workspace_snapshot()                     → full orientation (resets diff buffer)
screenshot(detail="text", windowTitle=X) → get actionable[].clickAt coords
mouse_click(x, y)                        → click directly, no math needed
screenshot(diffMode=true)                → check only what changed (~160 tok)

Security

Emergency stop (Failsafe)

Move the mouse to the top-left corner of the screen (within 10px of 0,0) to immediately terminate the MCP server.

• Per-tool check: checkFailsafe() runs before every tool handler

• Background monitor: 500ms polling as a backup for long-running operations

• Trigger radius: 10px

Blocked operations

workspace_launch blocklist: cmd.exe, powershell.exe, pwsh.exe, wscript.exe, cscript.exe, mshta.exe, regsvr32.exe, rundll32.exe, msiexec.exe, bash.exe, wsl.exe are blocked. Script extensions (.bat, .ps1, .vbs, etc.) are rejected. Arguments containing ;, &, |, `, $(, ${ are also rejected.

keyboard_press blocklist: Win+R (Run dialog), Win+X (admin menu), Win+S (search), Win+L (lock screen) are blocked.

PowerShell injection protection

All -like patterns in the UIA bridge PowerShell fallback path are sanitized with escapeLike(), which escapes wildcard characters (*, ?, [, ]) before they reach PowerShell. When the Rust native engine is active, PowerShell is not invoked for UIA operations.

Allowlist for workspace_launch

Shell interpreters are blocked by default. To allow specific executables, create an allowlist file:

File locations (searched in order):

1. Path in DESKTOP_TOUCH_ALLOWLIST environment variable

2. ~/.claude/desktop-touch-allowlist.json

3. desktop-touch-allowlist.json in the server's working directory

Format:

{
  "allowedExecutables": [
    "pwsh.exe",
    "C:\\Tools\\myapp.exe"
  ]
}

Changes take effect immediately — no restart needed.

Mouse movement speed

All mouse tools (mouse_move, mouse_click, mouse_drag, scroll) accept an optional speed parameter:

Default speed is 1500 px/sec. Change it permanently via the DESKTOP_TOUCH_MOUSE_SPEED environment variable:

{
  "mcpServers": {
    "desktop-touch": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@harusame64/desktop-touch-mcp"],
      "env": {
        "DESKTOP_TOUCH_MOUSE_SPEED": "3000"
      }
    }
  }
}

Common values: 0 = teleport, 1500 = default gentle, 3000 = fast, 5000 = very fast.

Force-Focus (AttachThreadInput)

Windows foreground-stealing protection can prevent SetForegroundWindow from succeeding when another window (such as a pinned Claude CLI) is in the foreground. This causes subsequent keystrokes or clicks to land in the wrong window — a silent failure.

mouse_click, keyboard_type, keyboard_press, and terminal_send all accept a forceFocus parameter that bypasses this protection using AttachThreadInput:

{
  "name": "mouse_click",
  "arguments": {
    "x": 500,
    "y": 300,
    "windowTitle": "Google Chrome",
    "forceFocus": true
  }
}

If the force attempt is refused despite AttachThreadInput, the response includes hints.warnings: ["ForceFocusRefused"].

Global default via environment variable:

{
  "mcpServers": {
    "desktop-touch": {
      "env": {
        "DESKTOP_TOUCH_FORCE_FOCUS": "1"
      }
    }
  }
}

Setting DESKTOP_TOUCH_FORCE_FOCUS=1 makes forceFocus: true the default for all four tools without changing each call.

Known tradeoffs:

• During the ~10ms AttachThreadInput window, key state and mouse capture are shared between the two threads. In rapid macro sequences this can cause a race condition (rare in practice).

• Disable forceFocus (or unset the env var) when the user is manually operating another app to avoid unexpected focus shifts.

Auto Guard (v0.12+)

Action tools (mouse_click, mouse_drag, keyboard_type, keyboard_press, click_element, set_element_value, browser_click_element, browser_navigate) automatically guard each action when you pass windowTitle / tabId:

• Verifies target window identity (process restart / HWND replacement detected)

• Confirms click coordinates are inside the target window rect

• Returns post.perception.status on every response — including failures — so the LLM can recover without a screenshot

Disabling auto guard — set DESKTOP_TOUCH_AUTO_GUARD=0 to restore v0.11.12 behavior (no auto guard):

{
  "mcpServers": {
    "desktop-touch": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@harusame64/desktop-touch-mcp"],
      "env": {
        "DESKTOP_TOUCH_AUTO_GUARD": "0"
      }
    }
  }
}

When auto guard is enabled (default), post.perception.status will be one of:

When unsafe_coordinates or identity_changed is returned, the response may include a suggestedFix.fixId. Pass that fixId to the relevant tool call to approve the recovery:

{ "name": "mouse_click",           "arguments": { "fixId": "fix-..." } }
{ "name": "keyboard_type",         "arguments": { "fixId": "fix-...", "text": "hello" } }
{ "name": "click_element",         "arguments": { "fixId": "fix-..." } }
{ "name": "browser_click_element", "arguments": { "fixId": "fix-..." } }

The fix is one-shot and expires in 15 seconds. The server revalidates the target process identity before executing.

v0.13 Additions

Target-Identity Timeline

The server tracks a semantic timeline of what happened to each target window/tab. Recent events are included in:

• get_history → recentTargetKeys: array of 3 most recently active target keys (compact, no event bodies)

• perception_read(lensId) → recentEvents: up to 10 events for that lens's target, each with tsMs, semantic, summary

Enable the MCP resources below to browse timelines:

{ "env": { "DESKTOP_TOUCH_PERCEPTION_RESOURCES": "1" } }

MCP resources available when enabled:

Manual Lens Eviction: FIFO → LRU

Manual lenses (created via perception_register) are now evicted by least-recently-used instead of insertion order. Using perception_read, evaluatePreToolGuards, or buildEnvelopeFor on a lens promotes it. The hard limit of 16 active lenses is unchanged.

browser_eval Structured Mode

Pass withPerception: true to receive a structured JSON response with post.perception instead of raw text:

{ "name": "browser_eval", "arguments": { "expression": "document.title", "withPerception": true } }

Returns { ok: true, result: "...", post: { perception: { status: "ok", ... } } }.

mouse_drag Cross-Window Guard

mouse_drag now guards both start and end coordinates. Drags that cross window boundaries (or reach the desktop wallpaper) are blocked by default. To allow intentional cross-window or range-selection drags:

{ "name": "mouse_drag", "arguments": { "startX": 100, "startY": 100, "endX": 900, "endY": 900, "allowCrossWindowDrag": true } }

Performance (v0.15 — Rust Native Engine)

The Rust native engine (@harusame64/desktop-touch-engine) replaces PowerShell process spawning with direct COM calls over a persistent MTA thread. It loads automatically as a .node addon — no configuration needed.

UIA Benchmark (vs PowerShell baseline)

Image Diff Benchmark (SSE2 SIMD)

Architecture

Claude CLI / MCP Client
    │  stdio or HTTP (MCP protocol)
    ▼
desktop-touch-mcp (TypeScript)
    │
    ├── Rust Native Engine (.node addon)          ← NEW in v0.15
    │   ├── UIA: 13 functions via napi-rs + windows-rs 0.62
    │   │   └── Dedicated COM thread (MTA) + batch BFS algorithm
    │   └── Image: SSE2 SIMD pixel diff + perceptual hashing
    │
    └── PowerShell Fallback (automatic)
        └── Activates transparently if .node is unavailable

Why getUiElements is 3.3× (not 160×)

The 160× speedup on getFocusedElement comes from eliminating PowerShell process startup (~200 ms) and .NET assembly loading. For getUiElements, the bottleneck shifts to the UIA provider inside the target application (e.g., Explorer) — it must enumerate its UI tree regardless of who asks. The Rust engine uses a batch BFS algorithm (FindAllBuildCache + TreeScope_Children) that minimizes cross-process RPC calls and supports maxElements early exit, making it dramatically faster on large trees (VS Code, browsers with 1000+ elements).

Known limitations

Token cost reference

License

MIT