claude-screen-mcp
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
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.
Related MCP server: Screen View MCP
Tools
Tool | Purpose |
| Capture a full display and resize the image result. |
| Capture a rectangular region. |
| Enumerate connected displays. |
| List visible top-level windows with optional title filter. |
| Run OCR on the full display or a region. |
| Search OCR text and return matching bounding boxes. |
| Capture only when perceptual-hash distance exceeds a threshold. |
| Return hash-distance diagnostics without an image. |
| Poll until the screen changes or a timeout elapses. |
| Sample a short interval and return deduplicated keyframes. |
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
Variable | Default | Purpose |
|
|
|
|
| Tesseract language list (allowlist enforced). |
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.mjsRoadmap
screenshot_window(title)for direct single-window capture.Improved multi-display enumeration on macOS and Linux.
License — MIT, see LICENSE.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Screenshot, PDF and HTML-to-image rendering API so Claude and Cursor can see any web page.
Screenshot, PDF and HTML-to-image rendering API so Claude and Cursor can see any web page.
Connect ChatGPT, Claude, Cursor or VS Code to your Windows PC: files, terminal, browser, apps.
Give your agent eyes: screenshots of any web page it can see, pages as markdown, and PDFs.
Related MCP Servers
- -licenseNot gradedqualityNot gradedmaintenanceProvides real-time screen capture streaming in base64 format via WebSocket connections, enabling Claude to view and analyze user screens through natural language requests.1-
- AlicenseDqualityDmaintenanceEnables AI assistants to capture and analyze screenshots using Claude Vision API, providing AI-powered insights about desktop interface content, UI elements, and visual layouts.2101 npm2MIT
- AlicenseNot gradedqualityDmaintenanceEnables Claude to remember and search everything that appeared on your screen using local OCR and embeddings. Provides tools for semantic search, activity timeline, and code change tracking.1MIT
- FlicenseAqualityDmaintenanceEnables Claude to capture screenshots, watch your screen in real-time, read text via OCR, and analyze video files, all running locally as an MCP server.14-