Claude Mobile
Control mobile devices (Android, iOS, Aurora OS) and desktop applications through natural language commands for automation, testing, and interaction.
Device & Platform Management: List connected devices across Android (via ADB), iOS Simulator (via simctl+WebDriverAgent), Desktop (Compose Multiplatform), and Aurora OS (via audb). Set active device and get system information.
UI Inspection & Interaction: Take screenshots (standard, auto-compressed, or annotated with numbered bounding boxes). Get UI hierarchy/accessibility tree. Tap, long press, and swipe by coordinates or element identification (text, resource ID, class name, index). Type text, press hardware buttons (BACK, HOME, VOLUME, etc.), and find/wait for elements.
App Management: Launch, stop, install apps (APK/RPM/.app bundles). Get current activity, list installed apps, manage permissions (grant/revoke/reset), and open URLs in device browsers.
System Operations: Execute shell commands, access device logs (logcat/system logs), inspect WebViews, and perform assertions for testing.
Desktop-Specific: Window management (resize, focus), clipboard operations, and performance metrics (CPU/memory).
Aurora OS-Specific: Push/pull files to/from device.
Efficiency: Batch commands for single round-trip execution. Available as Claude Code Plugin, npm package, or standalone native Rust CLI for CI/CD integration.
Enables mobile device automation for Android devices and emulators via ADB, including screenshot capture, UI interactions (tap, swipe, long press), text input, app control (launch, stop, install), hardware button presses, and UI hierarchy inspection.
Enables mobile device automation for iOS Simulator via simctl, including screenshot capture, UI interactions (tap, swipe, long press), text input, app control (launch, stop, install), and URL handling.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Claude Mobile take a screenshot of my android phone"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mcp-devices 4.2.0 (ex-claude-in-mobile)
👉 Want everything in one package? Keep using
claude-in-mobile.Nothing changes for you. Same install, all platforms bundled, still maintained:
npm i -g claude-in-mobileThat's it — the all-in-one edition. Read on only if you'd rather install the platforms separately (that's what
mcp-devicesis for).
Related MCP server: Android MCP Server
Two editions — same tool
Edition | Best for | Install |
| Want it all in one, zero setup |
|
| Want a slim base + only the platforms you need |
|
Both are maintained. claude-in-mobile was renamed to mcp-devices in 4.0 and
split into a modular edition; the all-in-one keeps its name and its unchanged
install. The rest of this README covers the modular mcp-devices edition.
Install in 3 steps (modular)
Requires Node.js 20 or newer.
# 1. base server
npm i -g mcp-devices
# 2. add a platform (example: Android)
npm i -g @mcp-devices/plugin-android
mcp-devices install android
# 3. point your MCP client at it
# { "mcpServers": { "mobile": { "command": "mcp-devices" } } }
# Grok Build:
# grok plugin marketplace add AlexGladkov/claude-in-mobile
# grok plugin install mcp-devices --trustRestart your MCP client. Done — ask Claude "take a screenshot of my Android device" and it works.
Check prerequisites any time: mcp-devices doctor.
Native shell CLI
The npm command mcp-devices is the Node.js MCP server. For direct shell
automation, install the native Rust CLI and use its unambiguous command name:
brew install AlexGladkov/tap/mcp-devices
mcp-devices-cli --help
mcp-devices-cli devicesThe separate name prevents a global npm install from shadowing the native CLI
on PATH.
Pick your platform
Each platform is a separate package. Install the one(s) you need — full guide in each doc:
Platform | Install | Needs | Guide |
Android |
|
| |
iOS |
|
| |
Web |
| Chrome | |
Desktop |
| Java/JDK | |
Aurora |
|
| |
HarmonyOS Next |
|
| |
All |
| — | — |
After installing a package, enable it: mcp-devices install <name> (or all),
then restart.
What it can do
Drive apps — screenshots, taps/swipes/typing, app launch, UI tree, shell, logs, permissions, files.
Debug live apps — breakpoints, stepping, inspect variables, evaluate expressions (Android JDWP + iOS LLDB). See debug ».
Test — visual regression, accessibility audit, performance, sensor/network simulation.
These come as ~20 built-in tool modules plus the on-demand debug plugin — full tool catalog ».
Switching from all-in-one to modular?
Happy with the bundled claude-in-mobile? Do nothing — it stays maintained
and installs exactly as before. This section is only if you want to move to the
slim modular edition.
The Node MCP commands
claude-in-mobileandmcp-deviceskeep working; the native shell interface is available asmcp-devices-cli.The only difference is that platforms aren't bundled — install the one(s) you actually use:
npm i -g mcp-devices
npm i -g @mcp-devices/plugin-android # (or plugin-all for everything)
mcp-devices install androidTools, actions, and MCP client config are identical to the bundled edition.
Docs
Modules & tools overview — how it's organized
Platforms: android · ios · web · desktop · aurora · harmony
Debug plugin — runtime debugging
Built-in tools reference — every tool + action
Notes
The modular base loads no platforms by default — enable them with
mcp-devices install <name>. Theclaude-in-mobileedition enables all.Enable the separately installed debug plugin with
mcp-devices plugin enable debug;MCP_DEVICES_TOOL_PLUGINS=debugremains available as a per-run override.Prefer everything in one package? Use the all-in-one
claude-in-mobileedition (npm i -g claude-in-mobile) — still maintained, install unchanged.
Available Tools
14 toolsappC
App lifecycle: launch, stop, install, list
Inputs: action (required), path, delayMs, package, +3 more.
deviceA
Device management + module loading. list/set/set_target/get_target: devices. enable_module/disable_module/list_modules: load browser/desktop/store tools on demand.
Inputs: action (required), module, target, category, +2 more.
flowA
Flow orchestration: batch (multi-command), run (multi-step automation with loops/conditionals), parallel (same action on multiple devices). Use turbo:true for rich feedback (experimental).
Inputs: action (required), args, steps, turbo, +5 more.
inputC
Input actions. tap/double_tap/long_press: coords or text/id/label/index. swipe: direction or coords. text: type text. key: press key.
Inputs: action (required), x, y, x1, +15 more.
repl_expectB
Block until a prompt regex matches, the session idles, the child exits, or the timeout fires.
Inputs: id (required), regex, idleMs, timeoutMs.
repl_keyA
Send a control key (enter/ctrl-c/ctrl-d/tab/arrows) to a session.
Inputs: id (required), key (required).
repl_killA
Terminate a REPL session (SIGTERM, then SIGKILL).
Inputs: id (required).
repl_listB
List active REPL sessions and their statuses.
Inputs: no named parameters.
repl_sendB
Write text to a REPL session. Appends a newline by default.
Inputs: id (required), text (required), newline.
repl_snapshotB
Read the current emulated terminal screen for a session. Output is redacted for common secret patterns unless disabled at plugin construction time.
Inputs: id (required), tail.
repl_spawnA
Start an interactive REPL or CLI process under a PTY. Returns the session id. cmd is exec'd directly (argv split, no shell): env-var prefixes, redirections (2>&1), pipes and globs are NOT interpreted — pass env via the env param, or set shell:true to run cmd through /bin/sh -c.
Inputs: id (required), cmd (required), cwd, env, +4 more.
screenB
Screen capture and annotation. capture: screenshot with compression/diff. annotate: screenshot with element bounding boxes.
Inputs: action (required), diff, preset, quality, +8 more.
systemC
System operations, clipboard, permissions, files. shell: run command. logs: device logs. clipboard_*: Android clipboard. permission_*: app permissions. file_*: Aurora file transfer.
Inputs: action (required), ms, tag, url, +10 more.
uiB
UI inspection and interaction. tree: accessibility tree. find: search elements. find_tap: fuzzy tap (Android). tap_text: tap by text (Desktop). analyze: screen analysis. wait/assert_visible/assert_gone: element checks.
Inputs: action (required), pid, text, fresh, +16 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 14 tools
Most tools have clear, distinct purposes (input vs. screen vs. ui vs. app lifecycle). However, 'input' and 'ui' both handle taps/texts, which could cause confusion; 'repl_*' tools are clearly separate but 'repl_spawn' vs 'repl_send' might overlap slightly in purpose.
Tools mostly follow single-word or verb_noun patterns, with 'repl_*' prefix consistently used. However, mixed styles like 'tap_text' vs 'find_tap' and 'repl_spawn' vs 'spawn' deviation from a uniform convention, though the naming is generally predictable.
14 tools is within the ideal 3-15 range, slightly on the higher end but each covers a distinct functionality area. The count feels appropriate for a mobile automation server, though some categories could be consolidated.
The tool surface covers core mobile automation needs: input, UI inspection, app lifecycle, device management, screen capture, and flow orchestration. Missing are some advanced operations like gesture composition or multi-touch, and the 'system' category is broad but shallow. Overall, no critical gaps for basic workflows.
Maintenance
Related MCP Connectors
Let AI agents control Android and iOS devices on Mobilerun Cloud: screen, input, apps, workflows.
Drive real Android & iOS devices and web browsers from natural language for mobile + web QA. 290+ tools across device control, app management, automation sessions, browser automation, and flow recording / replay. Bearer-auth — get a token at robotactions.com → Profile → API Tokens.
Give your AI agent a real cloud Android phone: push APKs, drive it, get screenshots and logs.
Let your AI agent control real iPhones: screenshots, tap, swipe, type and open apps.
Related MCP Servers
- FlicenseAqualityDmaintenanceEnables AI agents to interact with Android devices through UI manipulation, screen capture, touch gestures, text input, and app management via ADB. Provides comprehensive mobile automation capabilities including element detection, navigation, and application control for Android device testing and interaction.961 PyPI2-
- AlicenseBqualityDmaintenanceEnables control of Android devices via ADB, allowing screenshot capture, touch simulation, and swipe gestures through natural language commands.22188 npm6MIT
- AlicenseNot gradedqualityDmaintenanceEnables interaction with Android devices and emulators through ADB, allowing control actions like tapping, text input, screenshots, UI inspection, and app launching through natural language.13 npm8ISC
- AlicenseAqualityBmaintenanceEnables AI assistants to control mobile and desktop devices with natural language, including running automation tasks, taking screenshots, and managing devices.65 npmMIT