io.github.dockndevai/mcp-android·Other

mcp-android

Control Android devices over ADB from AI agents — safe-by-default, read-only by default, audited.

Stars
0
Version
0.1.0
License
MIT
Review
Passed
Language
TypeScript
Last commit
2h ago
Forks
0
Open issues
0
Registry update
Oct 14, 2026
adbandroiddevice-controlllmmcpmobilemodel-context-protocol

Connect

npm
Terminal
$claude mcp add mcp-android \  -e ANDROID_MODE=<android-mode> \  -e ANDROID_ADB_PATH=<android-adb-path> \  -e ANDROID_SERIAL=<android-serial> \  -e ANDROID_TIMEOUT_MS=<android-timeout-ms> \  -e ANDROID_PACKAGE_ALLOWLIST=<android-package-allowlist> \  -e ANDROID_PROTECTED_PACKAGES=<android-protected-packages> \  -e ANDROID_ALLOW_INSTALL=<android-allow-install> \  -e ANDROID_ALLOW_SHELL=<android-allow-shell> \  -e ANDROID_DRY_RUN=<android-dry-run> \  -e ANDROID_AUDIT_LOG=<android-audit-log> \  -- npx -y @dockndevai/[email protected]

Environment variables

  • ANDROID_MODE

    Access mode: read-only | read-write | admin.

  • ANDROID_ADB_PATH

    Path to the adb binary (default: adb on PATH).

  • ANDROID_SERIAL

    Target device serial from `adb devices`. Empty = the only connected device.

  • ANDROID_TIMEOUT_MS

    Per-command adb timeout in milliseconds.

  • ANDROID_PACKAGE_ALLOWLIST

    Comma-separated package allowlist for launch/uninstall/clear. Empty = all.

  • ANDROID_PROTECTED_PACKAGES

    Packages that can be launched/inspected but never uninstalled or data-cleared.

  • ANDROID_ALLOW_INSTALL

    Enable install_apk / uninstall_app / clear_app_data (requires admin mode too).

  • ANDROID_ALLOW_SHELL

    Enable run_shell (arbitrary adb shell; requires admin mode too).

  • ANDROID_DRY_RUN

    Validate + log write/admin actions without executing them on the device.

  • ANDROID_AUDIT_LOG

    Emit a JSON audit line to stderr per guarded operation (default true).

Security review

Review passed

Reviewed 38m ago.

metadata
scanned
packages
1 checked

No findings.

Tools

This server runs on your machine, so its tool list is not fetched before install — the README below describes what it offers.

mcp-android

CI License: MIT npm

A Model Context Protocol server to control an Android phone over ADB — the phone equivalent of the Mac-control servers. Claude can see the screen (screenshots + UI hierarchy) and tap, type, press keys, launch apps, set alarms/timers, and read notifications. Safe-by-default, with the suite's access-mode + flag model.

Runs on your computer and drives a phone connected by USB or wireless debugging (great for the Z Fold 7). It is not installed on the phone and does not need root.

iOS? A stock iPhone can't be controlled this way — Apple's sandbox forbids cross-app/system automation. See the separate mcp-ios repo for the realistic (Appium/WebDriverAgent over USB from a Mac) approach.

Quickstart

brew install android-platform-tools        # provides adb
# On the phone: Settings → Developer options → enable USB (or Wireless) debugging, then authorize this computer
adb devices                                 # confirm your device shows "device"

Run it straight from npm — no clone or build needed:

npx -y @dockndevai/mcp-android

Or add it to Claude Code in one line (start read-only):

claude mcp add android -e ANDROID_MODE="read-only" -- npx -y @dockndevai/mcp-android

See docs/CLIENTS.md for Claude Desktop, Cursor, Codex, Windsurf, and VS Code configs.

Setup from source

brew install android-platform-tools        # provides adb
adb devices                                 # confirm your device shows "device"
npm install && npm run build

Tools

Read (read-only+): list_devices, device_info, screenshot, ui_dump, current_app, list_apps, get_notifications

Write (read-write+): tap, swipe, input_text, press_key, launch_app, open_url, set_alarm, set_timer

Admin (admin): install_apk, uninstall_app, clear_app_data (need ANDROID_ALLOW_INSTALL), run_shell (needs ANDROID_ALLOW_SHELL; not registered otherwise)

The typical loop for driving the UI: screenshot → ui_dump (find bounds) → tap/input_text.

Security model

ConcernFlagDefault
What it can doANDROID_MODEread-only
Which packages in scopeANDROID_PACKAGE_ALLOWLIST(all)
Protected packages (never uninstall/clear)ANDROID_PROTECTED_PACKAGESsettings, systemui, gms
Allow install/uninstall/clearANDROID_ALLOW_INSTALLfalse
Allow raw adb shellANDROID_ALLOW_SHELLfalse
Interactive confirmation (destructive ops)MCP elicitation (client-driven)(on when the client supports it)
Preview without touching deviceANDROID_DRY_RUNfalse
Audit log (stderr)ANDROID_AUDIT_LOGtrue

When the connected client supports MCP elicitation, destructive tools (uninstall_app, clear_app_data, install_apk, run_shell) pause and ask the human to approve the exact action before it runs — the model can't approve on your behalf. When the client can't elicit, the access-mode + flag gates above are the control.

Run with Claude Desktop / Claude Code

{
  "mcpServers": {
    "android": {
      "command": "node",
      "args": ["/absolute/path/to/mcp-android/dist/index.js"],
      "env": { "ANDROID_MODE": "read-write" }
    }
  }
}

Example prompts

  • "Take a screenshot of my phone and tell me what's on screen."
  • "Set an alarm for 6:30am labeled Gym."
  • "Open the Clock app and start a 10-minute timer."
  • "What notifications do I have piling up?"

Develop

npm run dev
npm test          # security policy
npm run typecheck

License

MIT

From the server's repository — third-party content, read it before running anything it suggests.

More in Other

Listing from the official MCP Registry · repository facts from GitHub, 42m ago.