Controls a real iPhone through a $7 ESP32 board, so an AI vision model can tap, swipe, and type in any iOS app from an iPhone app, a CLI, or an MCP server.
Use it now
Keep it with up to 9 other tools you're setting up, then share them all as one link.
Try this first
Ask your assistant, with ESP32 iPhone Agent (Handsy) connected:
- Screenshot the iPhone
Use ESP32 iPhone Agent (Handsy) to capture the current iPhone screen from the board's AirPlay mirror: ‹what you need›
- Tap and Swipe
Use ESP32 iPhone Agent (Handsy) to tap on the iPhone screen: ‹what you need›
- Replay Runs
Use ESP32 iPhone Agent (Handsy) to replay a finished run step-by-step on the phone: ‹what you need›
Connect it over MCP
Connect ESP32 iPhone Agent (Handsy) as an MCP server, following its setup instructions at https://handsy.tech/docs/cli
Setup guide: handsy.tech/docs/cli
Install the CLI
npm install -g esp32agent
Setup guide: handsy.tech/docs/cli
Compare
Press Compare to add it to the tray at the bottom of the window, then pick up to 2 others anywhere on the site.
- Access
- CLIMCP
- Auth
- None
- Skills
- 4
Skills
Screenshot the iPhone
Captures the current iPhone screen from the board's AirPlay mirror so a vision model can decide on the next action.
Tap and Swipe
Taps, long-presses, and swipes on the iPhone screen through the board's USB mouse, with AssistiveTouch turning clicks into taps.
Type Text and Press Keys
Types text and presses keys and buttons on the iPhone through the board's USB keyboard; keyboard input from the CLI is ASCII only.
Replay Runs
Replays a finished run step by step on the phone with the taps and swipes drawn on top, and exports the trace for review.
