mcpField
A
AutoMobile

AutoMobile

Local
kaeawc.github.ioDeveloper Tools53Updated today
RepositoryVisit website

About AutoMobile

AutoMobile is an open-source MCP server for mobile engineers who want AI agents to explore and test Android and iOS apps. It combines device interaction with native test execution and performance checks.

Key features

  1. 01Android and iOS app interaction
  2. 02UX exploration and flow mapping
  3. 03Bug reproduction with screenshots
  4. 04Plain-language UI test plans
  5. 05Startup and scroll performance checks
  6. 06Native test execution across devices

Use cases

  1. 01Map an app’s screens and user flows
  2. 02Reproduce a reported bug with screenshots
  3. 03Generate executable UI test plans
  4. 04Check app launch and scrolling performance

MCP support

AutoMobile runs as an MCP server, exposing mobile device interaction and testing capabilities to compatible AI agents. It uses tools such as adb and simctl alongside Kotlin and Swift components.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "dev-jasonpearson-auto-mobile": {
      "command": "npx",
      "args": [
        "-y",
        "@kaeawc/auto-mobile"
      ]
    }
  }
}
Run commandnpx -y @kaeawc/auto-mobile

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@kaeawc/auto-mobile0.0.67

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

AutoMobile

Pull Request On Merge Nightly License

Platform: macOS Platform: Linux

TypeScript tests Kotlin tests Swift tests Kotlin coverage Swift coverage

AutoMobile sticker

AutoMobile lets AI agents control your mobile devices using natural language. Tell an AI what you want to do, and it interacts with your Android or iOS app.

It can do all this by being an MCP server that uses standard platform tools like adb & simctl paired with additional Kotlin & Swift libraries and apps. All components are open source. The point is to provide mobile engineers with AI workflow tools to perform UX deep dives, reproduce bugs, and run automated tests.

Setting an alarm in the Clock app An AI agent navigating to the Clock app, creating a new alarm

Searching YouTube for a video An AI agent searching YouTube and browsing results

Explore and Test
TaskWhat it does
Explore app UXNavigate your app, discover screens, map user flows, identify confusing interactions
Reproduce bugsPaste a bug report and get exact reproduction steps with screenshots
Create UI testsDescribe test scenarios in plain English, get executable test plans
Measure startup timeProfile cold and warm launch performance
Check scroll performanceDetect jank and dropped frames

How it works

  • 🤖 Fast UX Inspection Kotlin Accessibility Service and Swift XCTestService to enable fast, accurate observations. 10x faster than the next fastest observation toolkit.
  • 🦾 Full Touch Injection Tap, Swipe, Pinch, Drag & Drop, Shake with automatic element targeting.
  • ♻️ Tool Feedback Observations drive the interaction loop for all tool calls.
  • 🧪 Test Execution Kotlin JUnitRunner & Swift XCTestRunner execute tests natively handling device pooling, multi-device tests, and automatically optimizing test timing.

Get Started

You can use our interactive installer to step through all host platform requirements and configuration options. It checks host dependencies, optionally downloads Android or iOS developer tools, and configured the MCP daemon.

curl -fsSL https://raw.githubusercontent.com/kaeawc/auto-mobile/refs/heads/main/scripts/install.sh | bash

Prefer Homebrew for the CLI:

brew install kaeawc/tap/auto-mobile

or follow the installation guide.

Documentation

Contributing

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.