skills.rest
thomasttvo
thomasttvoCOMMUNITY
Explore all skills by this author →
GitHub

mobile-mcp

Automate screenshots, UI parsing, and gestures on iOS and Android devices.

Updated Aug 27, 2026
Search Tags:#mcp#mobile#gestures#metro#device-automation#omniparser#wda
One-click install
npx skills add https://github.com/thomasttvo/claude-skills --skill mobile-mcp-thomasttvo
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: mobile-mcp
Source: https://github.com/thomasttvo/claude-skills/tree/main/skills/mobile-mcp
Command: npx skills add https://github.com/thomasttvo/claude-skills --skill mobile-mcp-thomasttvo

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Mobile device interactions and test workflows are fragile and manual: capturing screenshots, identifying tappable elements, performing gestures, building and installing apps, and collecting React Native logs often require many manual steps and brittle tooling. This Skill unifies those capabilities into a single MCP server so agents and CI processes can reliably interact with physical iOS/Android devices and simulators.

Core Features & Use Cases

  • Build & Deploy: deterministic Metro port allocation, xcodebuild and Gradle build pipelines, cached installs for fast iteration.
  • Screenshots & Element Parsing: capture device screenshots, run OmniParser to extract tappable UI elements and return coordinates for safe automation.
  • Gestures & App Management: robust WDA-backed taps, swipes, pinches, key entry, launch/kill apps, and Android ADB fallbacks.
  • Debugging & Recovery: RN console capture via CDP, iOS unified logs, automatic port-forward/tunnel recovery, and WDA lifecycle management for resilient automation.
  • Use Case: run a CI-driven visual QA loop that builds the app, starts Metro, captures a screenshot, parses elements to locate a failing button, and issues a tap to reproduce and collect logs.

Quick Start

Start the mobile-mcp server and invoke the screenshot tool with the target device UDID to capture and parse the screen for tappable element coordinates.

Frequently Asked Questions about mobile-mcp

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate mobile UI testing on physical iOS and Android devices?▼

Automate mobile UI testing by capturing device screenshots, parsing tappable UI elements with OmniParser, and executing WDA-backed gestures on iOS and Android physical devices or simulators for reliable visual QA workflows.

Can I automate React Native Metro bundling and build pipelines for mobile apps?▼

Yes, you can automate React Native Metro bundling and build pipelines using deterministic Metro port allocation, xcodebuild and Gradle integrations, and cached installs to achieve fast iteration during mobile app deployments.

What's the best way to parse tappable UI elements from a mobile device screenshot?▼

The best way to parse tappable UI elements is using OmniParser to extract interactive components from device screenshots and return precise coordinates for safe automation and testing.

Does this mobile device automation tool support ADB fallbacks for Android gestures?▼

Yes, mobile device automation supports robust WDA-backed taps, swipes, and key entry, with Android ADB fallbacks to ensure reliable gesture execution and app lifecycle management across platforms.

How do I recover from port forwarding and tunnel failures during mobile automation?▼

Recover from port forwarding and tunnel failures during mobile automation using automatic recovery mechanisms and WDA lifecycle management, ensuring resilient and continuous automated testing workflows.

How do I collect React Native console logs and iOS unified logs for debugging?▼

Collect React Native console logs via CDP and iOS unified logs directly during automated workflows, capturing diagnostic output to debug issues while interacting with physical devices and simulators.

Related Skills

Explore More Software Engineering Skills→
softwarebyzesoftwarebyze

argent-android-emulator-setup

Boot Android emulators, select usable ADB device serials, and configure adb reverse for Metro.

Community
Intermediate
jamesrochabrunjamesrochabrun
194

qa-test-planner

Generate QA test plans, manual cases, regression suites, and bug reports.

Community
Advanced
aryaxtaryaxt

device

Build and install iOS apps on connected real devices using Xcodebuild.

Community
Intermediate
asnar00asnar00
1

eos-restart-app

Restart an installed Android app via adb force-stop and start commands.

Community
Intermediate