hridaya423/phonedriver

phonedriver lets Claude Code, Codex, Cursor or any MCP client use an Android phone or an iPhone. It reads the screen as text, which took 6.9x fewer tokens than mobile-mcp on nine phone jobs, and it asks you before it taps Pay.
One real Claude Code (Opus 5.5) session on an Android emulator, ordering on dominos.co.uk. The run took 6.5 minutes and is shown at 15x; the approval prompt plays at real speed. Nothing was ordered. Full video (MP4) .
## Start
sh
claude mcp add phonedriver -- npx -y phonedriver mcp
Start an Android emulator, plug in an Android phone with USB debugging on, or boot the iOS Simulator. Then give Claude a job that only a phone can do:
> Open my app, sign up with a new account, and tell me every bug you find on the way. Give me steps to reproduce each one.
> Find the app that drains my battery and tell me how long it ran in the background today.
> Go through my app's onboarding in dark mode and in light mode, and show me every screen where the text is hard to read.
The first run downloads one binary for your machine (macOS, Linux or Windows) and caches it. phonedriver doctor checks adb, Xcode and each device and tells you what to fix. Codex, Cursor and other clients: see Other clients. Homebrew, the shell installer and real iPhones: docs/reference.md.
Not released yet. Until the first release, build from source with cargo build --release .
## What the model sees
Each screen arrives as a short numbered list. This is the Settings app on an Android emulator:
console
$ phonedriver snapshot
app com.android.settings (Settings) · keyboard hidden · settled in 0ms
@e1 button "Search Settings"
@e2 group scrollable↓
@e3 button "Google" "Services & preferences"
@e4 button "Network & internet" "Mobile, Wi‑Fi, hotspot"
@e5 button "Connected devices" "Bluetooth, pairing"
...
@e10 button "Display & touch" "Dark theme, font size, touch"
The model taps by number. phonedriver waits until the screen stops changing, then replies. After tap @e10 the Display screen opens and the reply lists it, including @e24 switch "Dark theme" off. The next tap returns only what changed:
console
$ phonedriver tap @e24
ok tapped @e24 "Dark theme" at 353,532 · settled in 2034ms
~ @e23 button "Dark theme" "Will turn on when Bedtime starts" → "Will never turn off automatically"
~ @e24 switch "Dark theme" off → on
marks a line that appeared, - one that left, ~ one that changed. The model doesn't need to poll or guess how long a screen takes to load. It takes a screenshot only when it needs to see a picture.
## Fewer tokens
Tokens are what an agent's usage limit is spent on. I ran nine jobs that only a phone can do, twice each, with Claude Sonnet 5.5 and three MCP servers. The jobs included setting Chrome's search engine, cropping a photo, pinning and archiving Messages threads, finding the app that keeps the phone awake, and testing a sign-up flow for planted bugs. A script checked the phone's own data afterwards, not the model's report.
This is my own test set. All three tools ran on the same Android emulator on 10 November 2026. phone-harness used fewer tokens than phonedriver on two of the nine jobs. Every run, the versions, the checks and what was thrown away are published in docs/bench/jobs.md. If you maintain one of these tools and think I set it up wrong, open an issue and I will rerun it.