double_tap
Double-taps at coordinates on the device screen
LABSCO SUMMARY
Built for more than one device at a time, and it gives the agent the accessibility tree rather than only pixels.
Screenshots alone force a model to guess at coordinates; the flat UI tree, searchable and leaf-ranked, means it can find the element and then tap it. The scripting tool is the escape hatch for sequences that would take a dozen round trips — a short UIAutomator or XCUITest snippet runs on the device in one call.
What it is
A device-automation server with an on-device driver on each phone — UIAutomator on Android, XCUITest on iOS — normalised behind one flat element model.
What you get
- Device discovery across iOS and Android, with several devices driven in the same session
- The screen as a JPEG screenshot, and the UI as a flat element tree with search and a limit, off-screen elements dropped unless you ask for them
- Input that covers real interaction: tap, double-tap, long-press with a duration, swipe between coordinates, typing into the focused element, and hardware or navigation buttons including home, back and the d-pad
- App lifecycle: list what is installed, launch by bundle ID or package name, force-stop, and install from a file on the host — .apk on Android, .app or .ipa on iOS
- Sandboxed on-device scripting: UIAutomator-style JavaScript on Android with uiDevice, By and Until, and XCUITest-style JavaScript on iOS with app, springboard and openApp, each in a fresh sandbox with runaway scripts killed
- Bootstrapping handled for you — the driver app is installed, a port allocated and the on-device server started and health-checked on first use, then proxied over localhost with a per-device bearer token
Requirements
Node.js 18+ and the platform toolchain for whatever you are driving: the Android SDK with adb on PATH for Android, Xcode with xcrun and simctl for the iOS Simulator, and Xcode plus devicectl and iproxy for a real iOS device. Runs from npm as @srmorete/mobile-device-mcp over stdio; MDMS_PORT_ANDROID and MDMS_PORT_IOS set the base ports, assigned sequentially per device.
Setup effort
One command — npx -y @srmorete/mobile-device-mcp
USE CASES
01
Walking a flow on a real device to see whether it works
List the devices, launch the app, read the element tree, and tap and type your way through the steps.
02
Finding out why a screen looks wrong
Take the screenshot and pull the UI tree for the same moment, so layout and structure can be compared.
03
Testing a build you just produced
Install the .apk or .ipa from the host, launch it, and force-stop it between runs.
04
Checking the same journey on iOS and Android
Drive both devices in one session — the element model is the same shape on either platform.
05
Running a long interaction without a dozen round trips
Send a UIAutomator or XCUITest-style snippet to run in the on-device sandbox.
14 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
install_app
Installs an app on the device from a file on the host: .apk for Android, .app bundle for iOS simulator, .app or .ipa for iOS real device. Replaces existing installs.
launch_app
Launches an app on the device
list_apps
Lists installed apps on the device
list_devices
Lists available mobile devices
long_press
Long-presses at coordinates on the device screen
press_button
Presses a hardware/navigation button on the device
run_code
Execute test automation code on the device
screenshot
Takes a screenshot of the device screen
scroll
Scrolls on the device screen from start to end coordinates
tap
Taps at coordinates on the device screen
terminate_app
Terminates an app on the device
type_text
Types text on the device
uitree
Returns the UI element tree of the device screen. Off-screen elements are excluded by default; pass include_invisible: true to keep them. With search, results are ranked leaf-first (visible, non-container, smaller area).
BEFORE YOU INSTALL
What to know first
Tools you get
14 tools when we connected.
Requires
- npx on PATH
- Node.js 18+
CONTEXT COST
Light Standing cost
Rated by the size of the 14 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Add the block to your client, or run the command directly.
Server setup
Configuration file
JSON
{
"mcpServers": {
"mobile-device-mcp": {
"command": "npx",
"args": [
"-y",
"@srmorete/mobile-device-mcp"
]
}
}
}npx
TERMINAL
npx -y @srmorete/mobile-device-mcp
