Screenhand
Active·★ 15·AGPL-3.0·Updated 2026-04-02
ScreenHand is an open-source MCP server providing native desktop control for AI agents on macOS and Windows. It integrates Accessibility APIs, UI Automation, OCR, and Chrome DevTools Protocol to enable fast, robust interaction with applications and browsers, including multi-agent coordination and background job processing.
#Desktop Automation#AI Integration#UI Automation#Accessibility#OCR#Chrome DevTools Protocol#Multi-agent#Task Automation
01
Features
01Native UI control for macOS and Windows via Accessibility/UI Automation.
02Background Chrome browser control via DevTools Protocol.
03Extensive toolkit (82 tools) for cross-app automation and data extraction.
04Multi-agent coordination with session leases and stall detection.
05Persistent learning memory and background job processing daemon.
02
Compatibility
macOS
Platform
Verified via docs
Windows
Platform
Verified via docs
Node.js
Runtime
Verified via docs
MCP Clients
Integration
Verified via docs
Claude Desktop
AI Client
Verified via docs
Cursor
AI Client
Verified via docs
03
Quick start
1
$ git clone https://github.com/manushi4/screenhand.git
2
$ cd screenhand
3
$ npm install
4
$ npm run build:native
04
Use cases
↳AI-driven debugging and inspection of desktop application UIs.
↳Automating browser tasks like form filling, data scraping, and JavaScript execution via Chrome CDP.
↳Creating cross-application workflows by chaining actions across different desktop apps.
↳Coordinating multiple AI agents to control different application windows simultaneously without conflicts.
↳Processing multi-step automation jobs continuously in the background using a worker daemon.
05
Alternatives
Peekaboo★ 5.4k
Peekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models.
seline★ 172
Seline is a local-first AI desktop application that brings together conversational AI, visual generation tools, vector search, and multi-channel connectivity in one place.
ocr-mcp★ 23
FastMCP server providing advanced OCR capabilities with current state-of-the-art models (DeepSeek-OCR, Florence-2, DOTS.OCR, PP-OCRv5, Qwen-Image-Layered decomposition), WIA scanner control, and multi-format document processing for PDFs, CBZ comics, and images.
kreuzberg★ 9.4k
A polyglot document intelligence framework with a Rust core. Extract text, metadata, and structured information from PDFs, Office documents, images, and 50+ formats. Available for Rust, Python, Ruby, Java, Go, PHP, Elixir, C#, TypeScript (Node/Bun/Wasm/Deno)- or use via CLI, REST API, or MCP server.
native-devtools-mcp★ 139
MCP server for computer use & browser automation - screenshot, OCR, click, type, find_text, Chrome/Electron CDP, template matching. macOS, Windows & Android. Works with Claude, Cursor, and any MCP client.
ai-doc-gen★ 768
AI-powered multi-agent system that automatically analyzes codebases and generates comprehensive documentation. Features GitLab integration, concurrent processing, and multiple LLM support for better code understanding and developer onboarding.
Comments
Log in to leave a comment
No comments yet. Be the first!