Skip to main content
Glama

Sky Computer Use

Control your Mac from Android phone with AI.

Architecture

Android App ←→ WebSocket (8765) ←→ OpenCode Plugin ←→ MCP Binary ←→ Mac

Related MCP server: ScreenHand

Components

Android App

  • Real-time screen streaming

  • Tappable screenshot (click by coordinates)

  • Quick action buttons (keyboard shortcuts)

  • Chat with OpenCode agent

OpenCode Plugin

  • WebSocket server on port 8765

  • computer_use tool for AI agents

  • Auto-refresh screenshots

MCP Binary

  • open-computer-use npm package

  • Accessibility tree access

  • Element-based interactions

Quick Start

  1. Install OpenCode: curl -fsSL https://opencode.ai/install | bash

  2. Install MCP: npm i -g open-computer-use

  3. Start plugin (runs automatically with OpenCode)

  4. Start ngrok: ngrok http 8765

  5. Connect Android app to ngrok URL

Android App

Download: Releases

Usage

# In OpenCode, use computer_use tool:
computer_use(action="screenshot")
computer_use(action="click", element="42")
computer_use(action="type", text="hello")
computer_use(action="key", target="Return")

Related MCP Connectors

Related MCP Servers

  • A
    license
    Not graded
    quality
    F
    maintenance
    An experimental MCP server providing full control over the macOS user interface through mouse, keyboard, and window management tools. It enables AI assistants to automate desktop tasks by utilizing native accessibility APIs and OCR for real-time screen comprehension.
    7
    Creative Commons Zero v1.0 Universal
  • A
    license
    Not graded
    quality
    F
    maintenance
    An open-source MCP server for macOS and Windows that provides native desktop control via Accessibility APIs, OCR, and Chrome CDP. It enables AI agents to interact with applications, manage browser sessions, and automate workflows with high-speed native UI actions.
    29 npm
    15
    AGPL 3.0
  • A
    license
    Not graded
    quality
    D
    maintenance
    An MCP server for macOS that enables AI agents to control the desktop GUI through keyboard input, mouse actions, and screen captures. It provides stable low-level primitives for UI automation and agent-driven desktop workflows.
    MIT
  • A
    license
    B
    quality
    D
    maintenance
    MCP server that enables AI to fully control macOS — mouse, keyboard, terminal, screenshots, window management, UI element detection, and provides AI-optimized information reporting.
    36
    41 npm
    MIT