iPhone and iPad for your AI agents.
Your agent opens your iOS app, reads the screen and taps through it with the same API and MCP calls it uses on Android. Mobilebox iPhone sandboxes cost $0.05 a minute, billed by the second; its cloud Android phones cost $0.01 and were ready in 19.4 s in our November 2026 benchmark.
Sign up with GitHub. New workspaces get free credit.
- 1
Start with iPhone
Sign up and pick iPhone or iPad.
- 2
Create an iPhone
Your agent asks for
platform: "ios", over REST or MCP. - 3
Run your agent
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.
iPhone and iPad
- The same observe and act calls
- $0.05 per phone-minute
- Billed per second while it runs
Android too
- Cloud Android 14 phones (arm64)
- $0.01 per phone-minute
- One key for both
Getting started
- Sign up with GitHub
- Free credit for new workspaces
- Add credits from your dashboard
Questions
Getting started, pricing and the API.
How do I get iPhone sandboxes?
Sign up, create an API key, and ask for platform: "ios" when you create a phone. Your agent gets the same screen and actions as on Android.
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?
$0.05 per phone-minute for iPhone and iPad, billed by the second while the phone runs. Android cloud phones are $0.01 per phone-minute; dedicated devices start at $79 a month. See pricing.
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.