# Android Mobile

> Use this tool when you need to automate Android device interactions and test mobile apps, as it provides comprehensive workflows for UI analysis, touch interactions, text input, and app management. It solves problems related to automated mobile testing and app interaction, accepting inputs such as UI elements and coordinates, and producing outputs like screenshots and app listings. It is ideal for use cases involving AI assistants that require programmatic control over Android devices.

Canonical page: https://skillsregistry.net/skills/erichung9060-android-mobile  
JSON: https://api.skillsregistry.net/v1/skills/erichung9060-android-mobile

## Description

Android Mobile MCP bridges AI assistants with Android device automation through the uiautomator2 library, enabling comprehensive mobile app testing and interaction workflows. Built by erichung0906, it provides 9 core tools spanning UI analysis (hierarchical element extraction, screenshots), touch interactions (clicking with coordinate validation, swiping), text input, system navigation, and app management (listing and launching applications). The implementation uses XML parsing to extract focusable UI elements with calculated center coordinates, validates click targets against current UI state to prevent invalid interactions, and filters out system apps to show only user-accessible applications, making it valuable for automated mobile testing, app interaction workflows, and AI assistants that need to operate Android devices programmatically.

## Trust

- **Trust score (0–1):** 0.64
- **Verification tier:** scanned
- **Last scanned:** 2026-09-02

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-09-02

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/erichung9060-android-mobile)
- **Repository:** <https://github.com/erichung9060/android-mobile-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "erichung9060-android-mobile"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/erichung9060-android-mobile` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/erichung9060-android-mobile/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt