<div align="center">

🖐️ Grasp

Give Claude eyes and hands — full desktop control over MCP.

Grasp is a Model Context Protocol server that lets Claude see your screen and drive your mouse, keyboard and shell. Install it once and Claude Code — or any MCP host — can operate your Windows PC the way a person would: look, point, click, type, run commands.

</div>

---

What "eyes and hands" means. Eyes — Grasp captures the screen, resizes it to a vision-friendly resolution and draws a coordinate grid on top, so Claude can read exact positions instead of guessing. Hands — Grasp injects real, DPI-correct mouse and keyboard input at the OS level (a Rust backend), and runs shell commands directly. Together they close the loop: Claude looks, decides, acts, looks again.

Why Grasp

Most "computer use" setups are either a cloud VM you don't control, or a browser-only automation that can't touch the rest of your machine. Grasp runs locally, drives the real desktop, and plugs into the tools you already use through a single mcp add command.

• Pixel-perfect on scaled displays. The Rust input backend respects Windows display scaling (125% / 150% / 200%) — clicks land exactly where Claude looked, not two centimetres off.
• Vision tuned for accuracy. Screenshots are cropped/resized to ~1280 px with a 100-px coordinate grid overlay, the single biggest lever on click precision.
• Shell without the screenshot tax. run_command returns real text output — no opening a terminal, typing into it, and screenshotting the result.
• Safe by construction. Input is released on startup/shutdown so a stuck modifier can never freeze your keyboard; failing and elevated commands are reported honestly, never as silent successes.

Tools

	Tool	What it does
👁️	screenshot	Capture the screen (full or active window) as an image with a coordinate grid.
👁️	get_active_window	Title, process and bounds of the focused window.
👁️	list_windows	All open top-level windows.
👁️	get_screen_info	Monitor geometry, resolution and DPI scale.
✋	click	Glide the cursor to a point and click (left / right / middle).
✋	double_click	Double-click at a point.
✋	move_mouse	Move the cursor (to reveal hover-only menus).
✋	drag	Press, glide with the button held, release — selections, sliders, drag-and-drop.
✋	type_text	Type literal text at the current focus.
✋	press_key	Keys and combos: enter, ctrl+c, alt+f4, win+r, ctrl+shift+esc…
✋	scroll	Scroll up/down at a point.
⚙️	run_command	Run a shell command (PowerShell), optionally elevated via UAC; returns text output.
⚙️	wait	Pause N ms to let an app settle before the next screenshot.

How the coordinate model works

1. Claude calls screenshot. Grasp captures the screen, resizes the longest edge to 1280 px, and overlays a grid labelled every 100 px.
2. Claude reads a coordinate straight off the grid (e.g. "the button is near x≈540, y≈300").
3. Claude calls click with those numbers. Grasp maps them back through the resize + crop + DPI transform to the exact physical pixel and clicks there.

You never do the math — pass coordinates in the same space you see them. (Advanced: pass coord_space: "screen" to use raw physical pixels instead.)

Requirements

• Windows 10/11, x64. The mouse/keyboard backend ships as a prebuilt native binary for win32-x64. Screen capture, window enumeration and image processing are cross-platform, but Grasp is Windows-first today.
• Node.js ≥ 18.
• An MCP host — Claude Code, Claude Desktop, or anything that speaks MCP over stdio.

Install

git clone https://github.com/Jamshed7470/grasp-mcp.git
cd grasp-mcp
npm install
npm run doctor   # verify Grasp can see and control this machine

npm run doctor should end with ✅ Grasp is ready — Claude has eyes and hands.

Add to Claude Code

From the repo directory:

claude mcp add grasp -- node "%CD%\src\index.js"

…or with an absolute path from anywhere:

claude mcp add grasp -- node "C:\path\to\grasp-mcp\src\index.js"

Then just ask Claude, e.g. "take a screenshot and open Settings for me."

Add to Claude Desktop

Edit claude_desktop_config.json (%APPDATA%\Claude\claude_desktop_config.json) and add:

{
  "mcpServers": {
    "grasp": {
      "command": "node",
      "args": ["C:\\path\\to\\grasp-mcp\\src\\index.js"]
    }
  }
}

Restart Claude Desktop. Grasp's tools appear under the 🔨 menu.

Usage examples

Once installed, drive it in plain language — Claude picks the tools:

• "Open Notepad, type today's date, and save it to the Desktop."
• "Find the Wi-Fi icon in the tray and tell me which network I'm on." (screenshot → read)
• "Update all my winget packages." (run_command with elevated: true)
• "Scroll the page down and click the first search result."

Configuration

Environment variable	Purpose
GRASP_ENIGO_PATH	Absolute path to the node-enigo .node binary, if it isn't in the bundled native/ folder.

Per-tool options (image size, grid on/off, JPEG quality, command timeout, working directory, elevation) are passed as tool arguments — see each tool's description in the MCP schema.

⚠️ Security

Grasp gives an AI model real control of your computer — the same reach you have. Treat it accordingly.

• You are always in the loop. MCP hosts ask before each tool call by default. Keep it that way for anything destructive.
• Close sensitive windows (password managers, private messages) before running an agent — whatever is on screen is what Claude sees, and screenshots may briefly hold that content.
• Elevated commands need your hand. elevated: true triggers a Windows UAC prompt you must approve; UAC runs on a secure desktop that cannot be automated. If you dismiss it, Grasp reports the command as not run — never a silent success.
• Never commit screenshots. This repo's .gitignore blocks *.png/*.jpg for exactly this reason.
• Run Grasp only on machines and tasks you're comfortable handing to an assistant.

Troubleshooting

Symptom	Fix
enigo NOT loaded — hands disabled	The native binary wasn't found. Confirm native/node-enigo-win32-x64.node exists, or set GRASP_ENIGO_PATH. You're likely not on Windows x64.
node-screenshots NOT loaded	Run npm install (native module needs its prebuild).
Clicks land in the wrong place	Take a fresh screenshot right before clicking — coordinates are relative to the most recent capture.
run_command can't find cmd/ping/net	Grasp already restores PATH/PATHEXT for hosts that strip the environment; update to the latest version if you see this.

Run npm run doctor any time to re-check every backend.

How it's built

src/
  index.js            MCP server — registers the 13 tools over stdio
  native.js           screen capture + mouse/keyboard (node-enigo, node-screenshots, get-windows)
  image-processor.js  sharp pipeline: crop → resize → coordinate-grid overlay
  shell.js            PowerShell runner with UTF-8 output + UAC elevation
  doctor.js           standalone backend health check
native/
  node-enigo-win32-x64.node   prebuilt Rust input backend
test/
  mcp-test.js         end-to-end test over real MCP stdio (read-only + safe tools)
  live-notepad.js     opt-in live test that types into a throwaway file and reads it back

Backends: node-enigo (Rust, mouse/keyboard) · node-screenshots (Rust, capture) · get-windows · sharp · @modelcontextprotocol/sdk.

Development

npm run doctor          # health check, no server
node test/mcp-test.js   # 11 end-to-end assertions over MCP stdio
node test/live-notepad.js   # opt-in: drives the real desktop, cleans up after itself

Contributions welcome — especially a macOS/Linux input backend to make Grasp truly cross-platform.

License

MIT. Grasp bundles a prebuilt node-enigo binary and depends on node-screenshots, both built on the Rust enigo / xcap ecosystem.

<div align="center"> _{Grasp — <i>to grasp</i> is both to see and to hold. Built for Claude.} </div>