iPhone and iPad for your AI agents.
We set up iPhone and iPad for your app and your agent on a 30-minute call. After that, your agent opens your iOS app, reads the screen and taps through it with the same API and MCP calls it uses on Android.
Android cloud phones are self-serve. iPhone and iPad start with a 30-minute onboarding call.
- 1
Start with iPhone
Sign up and pick iPhone or iPad.
- 2
Book onboarding
A 30-minute call to set up iOS for your app and your agent.
- 3
Run your agent
After setup it reads the screen as numbered elements and taps, types and swipes by number, as on Android.
What you get
One API and one MCP server for every phone.
Android, self-serve
- Cloud Android 14 phones (arm64)
- REST and MCP, $0.01 per phone-minute
- Sign up and start in minutes
iPhone and iPad
- Set up on an onboarding call
- The same observe and act calls
- Pricing: talk to us
Getting started
- Sign up and pick iPhone or iPad
- Book the call from your dashboard
- The call is free
Questions
Setup, pricing and the API.
How do I get iPhone sandboxes?
Sign up, pick iPhone or iPad, and book a 30-minute onboarding call from your dashboard or here. We set you up from there.
Will it work with Claude Code, Codex and Cursor?
It uses the same hosted MCP server and REST API, so a client that drives Android phones makes the same calls.
What does it cost?
We price iPhone and iPad with you on the call: talk to us. Android cloud phones are $0.01 per phone-minute.
Read more
iOS testing for AI coding agents: what runs where today
Every iOS path for an agent runs on a Mac: Simulator, XCUITest, mobile-mcp, macOS CI runners and device farms, and where Mobilebox iPhone sandboxes fit.
Your agent built an iPhone app. How do you test it?
Simulator first, an outcome-based XCUITest second, a real iPhone third, then a device lab: a Mac-based checklist for iPhone apps an AI agent wrote.