"android" matching MCP servers:

Enables control of Android devices through ADB using natural language commands. Supports browser automation, SMS sending, device information retrieval, settings control, and common device actions like screenshots and button presses.

Enables LLMs to interact with MIT App Inventor, AndroidBuilder, Kodular, or Niotron IDEs in real-time, controlling the Designer and Blocks workspace via Chrome DevTools Protocol.

Enables Puppeteer-based web automation (navigation, screenshots, PDF generation, JavaScript execution, clicking) on Android Termux by running Chromium inside an Alpine Linux container.

Enables mobile device automation on Android and iOS via MCP, including native UI operations, WebView CDP debugging, and reusable JSON flow replay.

Melaya gives any AI access to your Android phone. And allows you to create AI agents in minutes.

MCP server for safety-first automation and app QA, exposing deterministic tools to control graphical apps, browsers, terminals, Android devices, VMs, and SSH hosts.

Real browser automation for Termux/Android. Runs Firefox or Chromium on Xvfb on your phone with a persistent daemon for sub-second commands.

Gives AI agents and MCP clients direct control over native desktop apps, Chrome/Electron browsers, and Android devices with screenshots, OCR, accessibility-based element lookup, input simulation, window management, CDP, and ADB in one local server.

A lightweight browser automation MCP server using raw Chrome DevTools Protocol, enabling web navigation, screenshots, and DOM interaction without heavy dependencies, and working on Termux/Android.

Provides bounded, observable access to graphical apps, browsers, terminals, Android devices, virtual machines, and SSH hosts through MCP tools, enabling safe automation and app QA.

Enables AI assistants to remotely control, debug, and automate real browsers, iOS simulators, and Android emulators, including navigation, element inspection, interaction, screenshots, and mobile gestures.

Modular testing and automation MCP servers for Android devices, desktop browsers, canvas games, and visual regression.

Enables coding agents to debug H5 pages running inside Android WebViews on real devices over adb and the Chrome DevTools Protocol, listing debuggable pages, streaming console output and uncaught exceptions, and evaluating JavaScript in the page without opening chrome://inspect.

Enables Claude Desktop to automate web browsers and mobile applications (iOS/Android) using WebDriverIO. Supports browser automation, mobile app testing, touch gestures, app lifecycle management, and hybrid app context switching through natural language.

Self-hosted anti-detect browser for AI agents. Rust MCP runtime + own Firefox engine fork (C++-level stealth). page_a11y: semantic snapshots pierce shadow DOM, detect login_state, danger zones, and prompt injection. Act by ref — no CSS selectors. Evidence recording, Android personas, 20 tools, 6 platforms.

Enables an MCP client to treat an app as a black box and probe its observable behavior across CLI, web, and Android targets, producing falsifiable rules, coverage gaps, and a sanitized spec for clean-room reimplementation.

Connects to the Firefox or Chromium browser you already use, on desktop or Android, so agents can navigate sites, read pages, click and fill forms, take screenshots, and extract structured data. It keeps session credentials inside the browser rather than copying them into agent configuration.

Enables AI agents to load web pages in true-to-size iPhone, iPad, and Android device frames, capture screenshots, inspect interactive elements and layout diagnostics, and automate tap/type/scroll flows with network mocks, console errors, and test evidence.

Enables an AI coding agent to drive a real Android phone over adb and one or more visible Chrome windows in the same test run, with safe guarded commands, screenshots returned as images, per-step logs, reports, and recordings. It lets agents act, inspect the screen and device log, fix code, and rerun a scenario until the feature passes.

Enables AI agents to observe and operate real desktops, mobile devices, and browser pages through screenshots, native accessibility trees, and web automation, including clicking, typing, hotkeys, and UI lookup across macOS, Linux, Windows, Android, and iOS.