mcpField
M
mobile-use-setup

mobile-use-setup

github.com/minitap-aiDevelopment3.3k37 installsUpdated 1w ago
Repository

About mobile-use-setup

A setup skill for configuring the mobile-use SDK to run an agent locally on a selected device. It guides developers through prerequisites, provider configuration, starter code, and verification.

Key features

  1. 01Choose iOS, Android, or both
  2. 02Configure local or cloud devices
  3. 03Set up an LLM provider
  4. 04Create and verify a local project

Use cases

  1. 01Prepare an SDK project for a physical device or emulator
  2. 02Configure a BrowserStack or Minitap cloud device
  3. 03Diagnose installation and device setup failures

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/minitap-ai/mobile-use --skill mobile-use-setup

After installing, type/mobile-use-setupin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

references/
android-device.md
ios-physical-device.md
scripts/
check-prerequisites.sh
create-project.sh
verify-device.sh

Details

From the project README

Mobile-Use SDK Setup

Set up mobile-use so the agent runs locally against a selected device.

Gather Requirements

Ask only for information not already provided:

  1. Target: iOS, Android, or both.
  2. Device path: local physical device/emulator, BrowserStack, or a Minitap cloud device.
  3. LLM provider: Minitap API, OpenAI, Anthropic, Google, OpenRouter, a local model, or another supported provider.

Check Prerequisites

python3 --version  # Requires 3.12+
which uv

# Android local
which adb
adb devices

# iOS simulator
which idb_companion
xcrun simctl list devices

# iOS physical
which idevice_id
which appium
appium driver list

For missing dependencies, use the device-specific reference files in this skill.

Create The Project

uv init <project-name>
cd <project-name>
uv add minitap-mobile-use python-dotenv
cp llm-config.override.template.jsonc llm-config.override.jsonc

Configure the selected provider in llm-config.override.jsonc and put only the required provider keys in .env. Add .env to .gitignore.

Create The Starter

Generate task code that runs the agent locally:

import asyncio

from dotenv import load_dotenv

from minitap.mobile_use.sdk import Agent
from minitap.mobile_use.sdk.builders import Builders
from minitap.mobile_use.sdk.types import AgentProfile

load_dotenv()


async def main() -> None:
    profile = AgentProfile(name="default", from_file="llm-config.override.jsonc")
    config = Builders.AgentConfig.with_default_profile(profile).build()
    agent = Agent(config=config)

    try:
        await agent.init()
        result = await agent.run_task(goal="Your automation goal", name="first-task")
        print(result)
    finally:
        await agent.clean()


if __name__ == "__main__":
    asyncio.run(main())

When selected, extend config with the BrowserStack or for_cloud_device(...) builder API.

Verify

Verify the selected device is visible, then run:

uv run python -c "from minitap.mobile_use.sdk import Agent; print('SDK OK')"
uv run python main.py

Diagnose setup failures from actual command output. Do not silently switch device paths.

Comments

Markdown supported