AndroidBuildMCP MCPサーバー

AndroidBuildMCP

Give your AI agent hands on Android. AndroidBuildMCP is an MCP server that lets any MCP client (Claude Code, Cursor, ...) build, deploy, drive and debug real Android apps: Gradle builds with readable errors, emulator management, adb deployment, logcat capture and full UI automation.

Quick start

Requirements: Node 18+, the Android SDK (ANDROID_HOME or a default install), and a JDK 17+ for Gradle builds.

No install step — npx fetches the server on first run.

Claude Code

claude mcp add androidbuild -- npx -y @asjackson/androidbuild-mcp

Any other MCP client

{
  "mcpServers": {
    "androidbuild": {
      "command": "npx",
      "args": ["-y", "@asjackson/androidbuild-mcp"]
    }
  }
}

git clone https://github.com/dev-jackson/androidbuild-mcp.git
cd androidbuild-mcp
npm install && npm run build
claude mcp add androidbuild -- node /absolute/path/to/androidbuild-mcp/dist/index.js

Then ask your agent to run doctor — it checks the SDK, adb, emulator, Java and connected devices, and tells you exactly what is missing.

What your agent can do

• Build and test — build_app compiles and returns compact file:line compiler errors instead of a thousand lines of Gradle noise. test_app / test_instrumented return parsed pass/fail summaries. Lint, clean, coverage (Kover/Jacoco) included.
• Manage emulators — list, create, boot (waits for full boot, returns the serial), wipe, and kill AVDs. Set GPS location, dark mode, and a clean demo status bar for screenshots.
• Deploy — build_run compiles, installs and launches in one call. Install/uninstall/clear-data/app-info via adb, with the right device auto-selected when only one is connected.
• See the screen — snapshot_ui returns the UI as a compact list of named elements with tap coordinates (Compose semantics merged, noise filtered). screenshot returns an image; with annotate: true it draws numbered boxes using vision, catching text inside images and WebViews.
• Touch the screen — tap, scroll, swipe, drag, long-press, type (keyboard-aware, with clear/submit), hardware keys, and wait_for_ui to poll until an element appears.
• Read the logs — background logcat capture filtered to your app, one-shot dumps, and the crash buffer for stack traces.
• Start new apps — scaffold_android_project generates a minimal Compose project that builds out of the box.

Session defaults (session_set_defaults) mean you configure project, module, variant and device once — every other call then works without arguments.

Tool reference

53 tools over stdio. Every tool takes plain arguments and returns text (or an image, for screenshot).

Environment and project

Tool	Description
doctor	Check SDK, adb, emulator, avdmanager, Java and connected devices; reports what is missing
discover_projects	Find Android/Gradle projects under a path
list_modules	List modules declared in settings.gradle(.kts)
list_variants	List build variants of a module
get_app_id	Read the applicationId of a module
show_gradle_config	Show Gradle, AGP, Kotlin and version-catalog entries

Session defaults

Tool	Description
session_set_defaults	Set default project, module, variant, serial and appId for all later calls
session_show_defaults	Show the current defaults
session_clear_defaults	Clear all defaults, or only the listed keys

Build, test and quality

Tool	Description
build_app	Build an APK; returns compact file:line compiler errors
build_run	Build, install and launch in one call
test_app	Run JVM unit tests with a parsed pass/fail summary
test_instrumented	Run instrumented tests on a device
lint	Run Android Lint and summarize the report
clean	Run gradle clean
get_apk_path	Locate the most recent APK without building
stop_gradle	Stop the project's Gradle daemons
get_coverage_report	Run Kover/Jacoco and summarize line coverage per package
get_file_coverage	Show covered/uncovered lines of one source file

Devices and emulators

Tool	Description
list_devices	List devices with serial, state, model, Android version, API level
list_avds	List AVDs and which are running
boot_emulator	Boot an AVD and wait for full boot; returns the serial
kill_emulator	Shut down a running emulator
create_avd	Create an AVD from an installed system image
delete_avd	Delete an AVD
set_emulator_location	Set GPS location
set_appearance	Switch dark/light mode
statusbar_demo_mode	Clean status bar for screenshots

App lifecycle

Tool	Description
install_app	Install an APK (adb install -r)
launch_app	Launch by application id, resolving the launcher activity
stop_app	Force-stop a running app
uninstall_app	Uninstall an app
clear_app_data	Reset an app to fresh-install state
get_app_info	Version, target/min SDK, install path, running PID

UI automation

Tool	Description
snapshot_ui	Dump the UI as named elements with exact tap coordinates
screenshot	Capture the screen; annotate: true draws numbered boxes
tap_element	Tap element #N from the last annotated screenshot
tap	Tap at pixels or screen percentages
scroll	Scroll in a direction with a safe computed swipe
swipe	Swipe between two points
drag	Drag from one point to another
long_press	Long-press, holding 1000 ms
type_text	Type into the focused field, waiting for the keyboard
key_press	Press BACK, HOME, ENTER, DPAD_*, or any keycode
key_sequence	Press several keys in order
wait_for_ui	Poll until an element appears

Logs and recording

Tool	Description
get_logs	One-shot logcat dump, filterable by app and tag
get_crash_logs	Crash buffer: Java exceptions, native crashes, ANRs
start_log_capture	Start background logcat capture to a file
stop_log_capture	Stop capture and return the file plus the last lines
record_video_start	Start screen recording (max 3 minutes)
record_video_stop	Stop recording and pull the MP4

Scaffolding

Tool	Description
scaffold_android_project	Create a minimal Compose app that builds out of the box

Tapping accurately

Everything adb-side shares one coordinate space (device pixels), but MCP clients often display screenshots scaled — estimating pixel positions by eye from the image sends taps to the wrong place. Three safe ways to hit the target:

1. snapshot_ui — returns exact device-pixel centers for every named element. Preferred.
2. screenshot { annotate: true } + tap_element { element: N } — tap by the number drawn on the image; the mapping is resolved on the original PNG, so client-side scaling cannot distort it.
3. tap { xPct, yPct } — screen percentages (0-1), also available on long_press/swipe/drag. Resolution-independent.

Raw tap { x, y } still works when you have real pixel coordinates.

Reliability

Every tool was exercised against real emulators and real projects — happy paths and corner cases — before release; the scenario-by-scenario evidence is in qa-results.md. Some of the details that keep agent flows from misfiring:

• type_text waits for the soft keyboard before injecting (typing right after focusing a field silently drops the first characters otherwise).
• scroll computes a long, slow swipe from the screen size — short fast swipes get ignored by some lists. long_press holds 1000 ms, which launchers require.
• Taps outside the screen are rejected with the actual screen size instead of silently doing nothing.
• Text-heavy screens (e-book WebViews and the like) are capped and searchable with snapshot_ui { filter } instead of flooding the context.
• Build/test/device failures come back as short, actionable messages with the next tool to call.

Optional extras

• Google's Android CLI enables screenshot { annotate: true }. doctor prints the one-line installer for your OS.
• The ADBKeyboard IME enables non-ASCII type_text (adb alone is ASCII-only). Install its APK once; the server uses it automatically.

Development

npm install
npm test            # unit tests (no real processes spawned)
npm run dev         # run the server from source
npm run build       # compile to dist/

License

MIT — see LICENSE.

Conceptually inspired by XcodeBuildMCP; independent implementation built around the Android toolchain.