Skip to main content
Glama
yagizdo
by yagizdo

Karagöz

Device automation for mobile apps. One tool, four targets: Android emulator, Android physical device, iOS simulator, iOS physical device. Works as a CLI, and as an MCP server when you want an AI agent driving it.

Status: early development. Nothing works yet. The design is settled, the code is not written.

What it does

Drive a device, observe the screen, touch it, capture what you see.

devices                       list and select a device
screenshot                    full resolution, with scale metadata
ui-tree                       accessibility tree, elements and bounding boxes
tap / swipe / text / key      interaction
install / launch / terminate  app lifecycle
logs                          device logs

Same commands across all four targets. One interface, four drivers.

Related MCP server: Android-MCP

What it is not

  • Not a test framework. No assertions, no test runner, no recorded flows, no retry policy, no reports.

  • Not a design comparison tool. Figma diffing, measurement and reporting belong a layer above. Karagöz produces the raw input; it does not interpret it.

It is the primitive layer. Each command does one thing and exits.

Name

Karagöz is Turkish shadow puppet theatre. Figures are driven with rods from behind a lit screen while the audience watches the movement on the screen. That is what this tool does.

Targets

Target

Transport

Android emulator

adb

Android device

adb over USB or Wi-Fi

iOS simulator

xcrun simctl plus an accessibility bridge

iOS device

tunnel plus WebDriverAgent / XCTest

Android comes first, iOS follows.

Requirements

Node 22 or newer. Platform tools are detected at runtime, not bundled: adb for Android, Xcode command line tools for iOS.

License

MIT

Related MCP Connectors

Related MCP Servers

  • F
    license
    A
    quality
    D
    maintenance
    Enables AI agents to interact with Android devices through UI manipulation, screen capture, touch gestures, text input, and app management via ADB. Provides comprehensive mobile automation capabilities including element detection, navigation, and application control for Android device testing and interaction.
    9
    4
    -
  • A
    license
    B
    quality
    B
    maintenance
    Enables AI agents to control Android devices and emulators through direct UI interaction, allowing app navigation, automated testing, and real-world task execution via ADB without computer vision or scripts.
    18
    2
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Enables AI assistants to control mobile and desktop devices with natural language, including running automation tasks, taking screenshots, and managing devices.
    6
    5 npm
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Enables AI agents to control, inspect, and automate Android devices, Waydroid containers, and AVD emulators over ADB. Provides tools for screenshots, UI-hierarchy text-based tapping, gestures, key presses, text input, app management, and raw shell commands.
    12
    MIT