QApilot MCP for Android - Android app testing inside your coding agent
by•
QApilot MCP automates tests on real Android devices and emulators by talking to Claude, Cursor or Codex. Describe a test flow in plain English, no Appium code required.
Your agent lays out the steps. QApilot runs the steps. It finds the elements, waits for the screen to settle, retries when something moves, and caches what it learns so repeat runs are faster. Every pass saves a Gherkin feature file and becomes a replayable test case.
Needs Node, Java and the Android SDK.
Replies
ResumeUp.AI
Really interesting approach. One thing I’m curious about: once QApilot learns the app’s UI and generates reusable tests, how well does it handle major UI changes between app versions?
Does it automatically adapt existing test cases, or would those need to be redefined?
QApilot
@rohithreddy - thank you. Small changes it handles. For instance, a moved or renamed element gets re-resolved at run time, since the saved test describes intent rather than a fixed locator.
Major redesigns should fail, and we'd rather they did than have it quietly match something else. What's missing is telling you it drifted, which a few people have asked for today.
The caching is the bit I'd worry about. If it remembers which elements it poked last run it stops looking, and a screen that quietly moved a button still passes because the cached path resolves fine. That's the failure I'd rather have loud and slow than fast and confident, and it's the same shape as every other agent problem, plausible output that nobody complains about. The Gherkin file falling out of each pass is the real feature, because it's the one artifact a human can read and disagree with.
QApilot
@asadmalik901 - Fair concern. The cache is a hint rather than a bypass, resolution still runs and the assertion still has to pass for the test, so a moved button only slips through if the cached path also satisfies the check.
Agreed on the Gherkin. It's the only artifact a human can argue with, which is why we write it on pass only.
This is pretty interesting. The ability to let the coding agent actually run flows on a local Android device and get the test result back in the same session feels really useful.
especially like the local-first approach and agent-readable reports. Nice launch 👏
QApilot
@adity_kushawaha thank you! exactly what we felt important to implement to make it genuinely useful to developers. Results in the same session and local-first approach. Glad it resonates.
You're telling me that i dont have to tap through the same login screen 50 times a day anymore?😲Sounds like magic. Whats the wierdest bug your AI has caught so far?