ZBS Index What actually exists in applied AI, with the source next to it

mcp server

agent-device

Let AI agents inspect, control, and debug real iOS, Android, desktop, and TV apps

Description as published by the maintainer. Source

  • version 0.16.9
  • active

active — Most recent push to the repository was 2026-08-06.

Signals

These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.

Signal Value What it measures Window Observed Source
GitHub stars 3,993 Number of GitHub accounts that bookmarked this repository since it was created. It is a bookmark count, not installs, not active users and not quality. cumulative, all time GitHub
Last commit 2026-08-06 Date of the most recent push to any branch. This is the strongest cheap indicator of whether the project is still maintained. point in time GitHub
Open issues 57 Open issues plus open pull requests, as GitHub counts them together. A high number can mean an active project or an abandoned one. as of fetch GitHub
Latest published version 0.16.9 Latest version string the maintainer published to the registry. as of fetch Model Context Protocol
Registry record last updated 2026-06-01 When the registry record was last updated by its maintainer. point in time Model Context Protocol
License MIT Licence GitHub detected in the repository. Detection can be wrong; the LICENSE file is authoritative. as of fetch GitHub
First listed in the MCP Registry 2026-06-01 Date this server was first published to the official MCP Registry. Not a usage or quality measure. point in time Model Context Protocol
repository status active The repository exists on GitHub and is not archived. This says nothing about how recently it was worked on. as of fetch GitHub

Where to get it

Related, by what their authors tagged them

  • io.github.aarwitz/tapp — last commit 2026-07-30, shares e2e-testing, ios-simulator, testing
    Autonomous QA for iOS + web — agents get a deterministic ship/no-ship verdict, no test code
  • Drengr — last commit 2026-08-01, shares agentic-ai, e2e-testing, mobile-testing
    Eyes and hands for AI agents on Android and iOS devices.
  • io.github.ai-dashboad/flutter-skill — last commit 2026-07-23, shares automation, e2e-testing, flutter
    AI-powered E2E testing for 10 platforms. 253 MCP tools. Zero test code needed.
  • App Store Trends API — last commit 2026-08-03, shares mobile
    App downloads and chart ranking trends for iOS and Android. Free key at trendsapi.ai
  • Antigravity Link — last commit 2026-06-04, shares mobile
    MCP server and OpenAPI-backed mobile companion for controlling Antigravity IDE sessions
  • Vibe Test — Browser Testing Agent — last commit 2026-06-08, shares e2e-testing, testing
    Code-aware browser testing agent — 13 Playwright tools for AI code editors via MCP
  • CometChat Docs — last commit 2026-07-20, shares flutter, react-native
    CometChat docs search + implementation bundles: add chat, voice, video & moderation to your app.
  • io.github.Anandb71/arbor — last commit 2026-08-03, shares flutter
    The Graph-Native Intelligence Layer for Code.
  • PRD to Flutter APK — last commit 2026-08-05, shares flutter
    Generate a Flutter app from a JSON spec free; pay only for the compiled APK (USDC on Base).
  • VULK — last commit 2026-05-25, shares flutter
    Generate, edit, and deploy immersive 3D/WebGL web projects from any MCP assistant.

These share tags the maintainers applied themselves, such as e2e-testing, ios-simulator, testing, xcuitest. Common tags like "mcp" or "ai" are ignored for this: agreeing with six hundred other projects is not a similarity.

This is not a recommendation and not a test result. It is a map of what the authors said their work is about.

How the author describes it

Topics the maintainer set on GitHub: adb, agentic-ai, agents, ai-agents, android-emulator, automation, e2e-testing, expo, flutter, ios-simulator, mcp, mobile, mobile-testing, performance-optimization, react-native, testing, xcuitest.

Bring your own setup

We take apart real AI setups every week and show what broke, what cost too much, and what the trace actually said. If you run agents on real work, that is where the useful conversation is.

Join ZBS AI Practice Lab

Sources

  1. callstackincubator/agent-device on GitHub — GitHub, observed , trust tier 3.
  2. Official MCP Registry — Model Context Protocol, observed , trust tier 1.