What can you do with this server?

Control mobile devices (Android, iOS, Aurora OS) and desktop applications through natural language commands for automation, testing, and interaction. Device & Platform Management: List connected devices across Android (via ADB), iOS Simulator (via simctl+WebDriverAgent), Desktop (Compose Multiplatform), and Aurora OS (via audb). Set active device and get system information. UI Inspection & Interaction: Take screenshots (standard, auto-compressed, or annotated with numbered bounding boxes). Get UI hierarchy/accessibility tree. Tap, long press, and swipe by coordinates or element identification (text, resource ID, class name, index). Type text, press hardware buttons (BACK, HOME, VOLUME, etc.), and find/wait for elements. App Management: Launch, stop, install apps (APK/RPM/.app bundles). Get current activity, list installed apps, manage permissions (grant/revoke/reset), and open URLs in device browsers. System Operations: Execute shell commands, access device logs (logcat/system logs), inspect WebViews, and perform assertions for testing. Desktop-Specific: Window management (resize, focus), clipboard operations, and performance metrics (CPU/memory). Aurora OS-Specific: Push/pull files to/from device. Efficiency: Batch commands for single round-trip execution. Available as Claude Code Plugin, npm package, or standalone native Rust CLI for CI/CD integration.

Which integrations are available for this server?

Enables mobile device automation for Android devices and emulators via ADB, including screenshot capture, UI interactions (tap, swipe, long press), text input, app control (launch, stop, install), hardware button presses, and UI hierarchy inspection. Enables mobile device automation for iOS Simulator via simctl, including screenshot capture, UI interactions (tap, swipe, long press), text input, app control (launch, stop, install), and URL handling.

How do I use Claude Mobile?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Claude Mobile take a screenshot of my android phone" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

Claude Mobile

MCP server for mobile and desktop automation — Android (via ADB), iOS Simulator (via simctl), Desktop (Compose Multiplatform), and Aurora OS (via audb). Like Claude in Chrome but for mobile devices and desktop apps.

Control your Android phone, emulator, iOS Simulator, Desktop applications, or Aurora OS device with natural language through Claude.

Features

Unified API — Same commands work for Android, iOS, Desktop, and Aurora OS
Smart screenshots — Auto-compressed for optimal LLM processing (no more oversized images!)
Annotated screenshots — Screenshots with colored bounding boxes and numbered element labels for visual UI understanding
Permission management — Grant, revoke, and reset app permissions programmatically (Android runtime permissions, iOS privacy services)
Device logs — Read logcat/system logs with filters for debugging
UI interactions — Tap, long press, swipe by coordinates or element text
Text input — Type into focused fields
App control — Launch, stop, and install apps
Platform selection — Explicitly target Android, iOS, Desktop, or Aurora OS
Desktop support — Test Compose Multiplatform desktop apps with window management, clipboard, and performance metrics

Installation

Claude Code CLI (recommended)

claude mcp add --transport stdio mobile -- npx -y claude-in-mobile

To add globally (available in all projects):

claude mcp add --scope user --transport stdio mobile -- npx -y claude-in-mobile

From npm

npx claude-in-mobile

From source

git clone https://github.com/AlexGladkov/claude-in-mobile.git cd claude-in-mobile npm install npm run build:all # Builds TypeScript + Desktop companion

Note: For Desktop support, you need to run npm run build:desktop (or build:all) to compile the Desktop companion app.

Manual configuration

Add to your Claude Code settings (~/.claude.json or project settings):

{ "mcpServers": { "mobile": { "command": "npx", "args": ["-y", "claude-in-mobile"] } } }

Windows

claude mcp add --transport stdio mobile -- cmd /c npx -y claude-in-mobile

Requirements

Android

ADB installed and in PATH
Connected Android device (USB debugging enabled) or emulator

iOS

macOS with Xcode installed
iOS Simulator (no physical device support yet)
WebDriverAgent for full UI inspection and element-based interaction:
npm install -g appium appium driver install xcuitest
Or set WDA_PATH environment variable to custom WebDriverAgent location

Desktop

macOS (Windows/Linux support planned)
JDK 17+ for building the Desktop companion
Compose Multiplatform desktop application to test

Aurora OS

audb CLI installed and in PATH (cargo install audb-client)
Connected Aurora OS device with SSH enabled
Python on device required for tap/swipe: devel-su pkcon install python

Available Tools

Core Tools (All Platforms)

Tool	Android	iOS	Desktop	Aurora	Description
`list_devices`	✅	✅	✅	✅	List all connected devices
`set_device`	✅	✅	✅	✅	Select active device
`screenshot`	✅	✅	✅	✅	Take screenshot
`tap`	✅	✅	✅	⚠️	Tap at coordinates or by text/label (iOS: WDA required for element tap)
`long_press`	✅	✅	✅	✅	Long press gesture
`swipe`	✅	✅	✅	⚠️	Swipe in direction or coordinates (requires Python on Aurora)
`input_text`	✅	✅	✅	❌	Type text
`press_key`	✅	✅	✅	✅	Press hardware buttons
`launch_app`	✅	✅	❌	✅	Launch app
`stop_app`	✅	✅	❌	✅	Stop app
`install_app`	✅	✅	❌	✅	Install APK/.app/.rpm
`list_apps`	❌	❌	❌	✅	List installed apps (Aurora only)
`get_ui`	✅	✅	✅	❌	Get UI hierarchy (iOS: requires WebDriverAgent)
`find_element`	✅	✅	✅	❌	Find elements by text/id/label (iOS: requires WebDriverAgent)
`annotate_screenshot`	✅	✅	❌	❌	Screenshot with colored bounding boxes and numbered element labels
`grant_permission`	✅	✅	❌	❌	Grant app permission (Android: runtime, iOS: privacy service)
`revoke_permission`	✅	✅	❌	❌	Revoke app permission
`reset_permissions`	✅	✅	❌	❌	Reset all permissions for an app
`get_current_activity`	✅	❌	❌	❌	Get foreground activity
`open_url`	✅	✅	❌	❌	Open URL in browser (not yet implemented on Aurora)
`shell`	✅	✅	❌	✅	Run shell command
`wait`	✅	✅	✅	✅	Wait for duration
`get_logs`	✅	✅	❌	✅	Get device logs (logcat/system log)
`clear_logs`	✅	⚠️	❌	✅	Clear log buffer
`get_system_info`	✅	❌	❌	✅	Battery, memory info
`wait_for_element`	✅	✅	❌	❌	Wait for element to appear (polling + timeout)
`assert_visible`	✅	✅	❌	❌	Assert element is visible (pass/fail)
`assert_not_exists`	✅	✅	❌	❌	Assert element does NOT exist (pass/fail)
`batch_commands`	✅	✅	✅	✅	Execute multiple commands in single round-trip
`get_webview`	✅	❌	❌	❌	Inspect WebView via Chrome DevTools Protocol
`push_file`	❌	❌	❌	✅	Upload file (Aurora only)
`pull_file`	❌	❌	❌	✅	Download file (Aurora only)

Desktop-Specific Tools

Tool	Description
`set_target`	Set target platform (android/ios/desktop)
`get_target`	Get current target platform
`launch_desktop_app`	Launch a Compose Desktop application
`stop_desktop_app`	Stop the running desktop application
`get_window_info`	Get desktop window position and size
`focus_window`	Bring desktop window to front
`resize_window`	Resize desktop window
`get_clipboard`	Get system clipboard content
`set_clipboard`	Set system clipboard content
`get_performance_metrics`	Get CPU/memory usage of desktop app

For detailed Desktop API documentation, see Desktop Specification

Usage Examples

Just talk to Claude naturally:

"Show me all connected devices" "Take a screenshot of the Android emulator" "Take a screenshot on iOS" "Tap on Settings" "Swipe down to scroll" "Type 'hello world' in the search field" "Press the back button on Android" "Open Safari on iOS" "Switch to iOS simulator" "Run the app on both platforms"

Permission Management

"Grant camera permission to com.example.app on Android" "Revoke location access from com.example.app" "Reset all permissions for com.apple.Maps on iOS"

Annotated Screenshots

"Take an annotated screenshot" → Screenshot with green (clickable) and red (non-clickable) bounding boxes + numbered element index

Platform Selection

You can explicitly specify the platform:

"Screenshot on android" → Uses Android device "Screenshot on ios" → Uses iOS simulator "Screenshot on desktop" → Uses Desktop app "Screenshot on aurora" → Uses Aurora OS device "Screenshot" → Uses last active device

Or set the active device:

"Use the iPhone 15 simulator" "Switch to the Android emulator" "Switch to desktop" "Switch to Aurora device"

Desktop Examples

"Launch my desktop app from /path/to/app" "Take a screenshot of the desktop app" "Get window info" "Resize window to 1280x720" "Tap at coordinates 100, 200" "Get clipboard content" "Set clipboard to 'test text'" "Get performance metrics" "Stop the desktop app"

Aurora Examples

"List all Aurora devices" "Take a screenshot on Aurora" "Tap at coordinates 100, 200 on Aurora" "Launch ru.example.app on Aurora" "List installed apps on Aurora device" "Get logs from Aurora device" "Push file.txt to /home/defaultuser/ on Aurora device"

Native CLI

A 2 MB native Rust binary with all the same commands. No Node.js, no dependencies.

Install CLI

brew tap AlexGladkov/claude-in-mobile brew install claude-in-mobile

Or download from Releases.

Advantages over MCP

Easy install — brew install or copy a single 2 MB binary
No dependencies — no Node.js, no npm, nothing
Use from terminal — run commands directly, no Claude Code or MCP client needed
Test automation — write universal .sh scripts for any platform without learning platform internals
Token-efficient — skill documentation loads only when used; MCP loads all tool schemas into every request, which adds up fast over a session
Fast — ~5ms command startup (Rust) vs ~500ms (Node.js MCP)
CI/CD ready — exit codes, stdout/stderr, runs anywhere

Test script example

#!/bin/bash claude-in-mobile launch android com.example.app claude-in-mobile wait 2000 claude-in-mobile tap android 0 0 --text "Login" claude-in-mobile input android "test@example.com" claude-in-mobile screenshot android -o result.png claude-in-mobile ui-dump android | grep "Welcome" && echo "PASS" || echo "FAIL"

Claude Code Plugin

claude plugin marketplace add AlexGladkov/claude-in-mobile claude plugin install claude-in-mobile@claude-in-mobile

After installing, Claude Code controls devices with natural language. The skill loads into context only on demand — no token overhead when not in use.

See cli/README.md for full CLI documentation.

iOS WebDriverAgent Setup

For full iOS UI inspection and element-based interaction, WebDriverAgent is required. It enables:

get_ui - JSON accessibility tree inspection
tap with label or text parameters - Element-based tapping
find_element - Element discovery and querying
swipe - Improved gesture simulation

Installation

Automatic (via Appium):

npm install -g appium appium driver install xcuitest

Manual: Set the WDA_PATH environment variable to your WebDriverAgent location:

export WDA_PATH=/path/to/WebDriverAgent

First Use

On first use, WebDriverAgent will be automatically:

Discovered from Appium installation or WDA_PATH
Built with xcodebuild (one-time, ~2 minutes)
Launched on the iOS simulator
Connected via HTTP on port 8100+

Troubleshooting

Build fails:

# Install Xcode command line tools xcode-select --install # Accept license sudo xcodebuild -license accept # Set Xcode path sudo xcode-select -s /Applications/Xcode.app

Session fails:

Ensure simulator is booted: xcrun simctl list | grep Booted
Check port availability: lsof -i :8100
Try restarting the simulator

Manual test:

cd ~/.appium/node_modules/appium-xcuitest-driver/node_modules/appium-webdriveragent xcodebuild test -project WebDriverAgent.xcodeproj \ -scheme WebDriverAgentRunner \ -destination 'platform=iOS Simulator,id=<DEVICE_UDID>'

How It Works

┌─────────────┐ ┌──────────────────┐ ┌─────────────────┐ │ Claude │────▶│ Claude Mobile │────▶│ Android (ADB) │ │ │ │ MCP Server │ └─────────────────┘ │ │ │ │ ┌─────────────────┐ │ │ │ │────▶│ iOS (simctl+WDA)│ │ │ │ │ └─────────────────┘ │ │ │ │ ┌─────────────────┐ │ │ │ │────▶│ Desktop (Compose)│ │ │ │ │ └─────────────────┘ │ │ │ │ ┌─────────────────┐ │ │ │ │────▶│ Aurora (audb) │ └─────────────┘ └──────────────────┘ └─────────────────┘

Claude sends commands through MCP protocol
Server routes to appropriate platform (ADB, simctl+WDA, Desktop companion, or audb)
Commands execute on your device or desktop app
Results (screenshots, UI data, metrics) return to Claude

License

MIT

Claude Mobile

Claude Mobile

Features

Installation

Claude Code CLI (recommended)

From npm

From source

Manual configuration

Windows

Requirements

Android

iOS

Desktop

Aurora OS

Available Tools

Core Tools (All Platforms)

Desktop-Specific Tools

Usage Examples

Permission Management

Annotated Screenshots

Platform Selection

Desktop Examples

Aurora Examples

Native CLI

Install CLI

Advantages over MCP

Test script example

Claude Code Plugin

iOS WebDriverAgent Setup

Installation

First Use

Troubleshooting

How It Works

License

Resources

Tools

Latest Blog Posts

MCP directory API