claude-screen-mcp

An MCP server that exposes read-only screen state. Capture, OCR, and change detection only — no input control.

Quick start

git clone https://github.com/lfzds4399-cpu/claude-screen-mcp
cd claude-screen-mcp
npm install
npm run build

claude mcp add screen -- node "$(pwd)/dist/index.js"

Restart the MCP host after registration.

Tools

Platform support

Windows 10+ is the primary target and is exercised on every release. macOS 11+ and Linux (X11 and Wayland) pass CI and smoke tests but are not regularly exercised. Window enumeration on macOS and Linux requires platform tooling; multi-monitor display enumeration is supported on Windows.

Security and privacy

All processing is local. No screenshot, OCR text, or telemetry leaves the machine; the only network call is the initial Tesseract language data download.

OCR output is untrusted input. Text rendered on screen may attempt to influence the model. Treat output as user-supplied data and avoid auto-executing commands derived from it. Scope read_screen_text to a window when full-desktop capture is not required.

Configuration

The first OCR call downloads language data (~10MB per language); subsequent calls reuse the local cache.

Development

npm install
npm run build
npm test
node tests/e2e-wire.mjs

Roadmap

• screenshot_window(title) for direct single-window capture.

• Improved multi-display enumeration on macOS and Linux.

License — MIT, see LICENSE.