AutoMobile
An MCP server that enables AI agents to control Android and iOS devices via natural language, using platform tools like adb and simctl.
README
AutoMobile
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.
An AI agent navigating to the Clock app, creating a new alarm
An AI agent searching YouTube and browsing results
Explore and Test
| Task | What it does |
|---|---|
| Explore app UX | Navigate your app, discover screens, map user flows, identify confusing interactions |
| Reproduce bugs | Paste a bug report and get exact reproduction steps with screenshots |
| Create UI tests | Describe test scenarios in plain English, get executable test plans |
| Measure startup time | Profile cold and warm launch performance |
| Check scroll performance | Detect jank and dropped frames |
| Audit contrast | Find accessibility issues with color contrast |
| Check tap targets | Ensure touch targets meet size guidelines |
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
or you can read and follow the step-by-step manual guide.
Documentation
- Full Documentation - Complete guide with examples
- FAQ - Common questions answered
- Design Docs - Architecture and implementation details
Contributing
- Code of Conduct
- Please report security vulnerabilities via GitHub
- Contributing
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.