adb-mcp

<div align="center">
<img src="assets/android-head_flat.svg" width="72" alt="Android robot logo">

# adb-mcp

**An [MCP](https://modelcontextprotocol.io) server that drives Android emulators and devices over `adb`**

[![Website](https://img.shields.io/badge/website-adb--mcp.com-3DDC84?logo=vercel&logoColor=white)](https://adb-mcp.com)
[![Release](https://img.shields.io/github/v/release/iksnerd/adb-mcp?logo=github&color=3DDC84)](https://github.com/iksnerd/adb-mcp/releases/latest)
[![CI](https://github.com/iksnerd/adb-mcp/actions/workflows/ci.yml/badge.svg)](https://github.com/iksnerd/adb-mcp/actions/workflows/ci.yml)
[![Go](https://img.shields.io/badge/Go-1.26%2B-00ADD8?logo=go&logoColor=white)](go.mod)
[![MCP](https://img.shields.io/badge/MCP-stdio-3DDC84)](https://modelcontextprotocol.io)

</div>

---

Boot an AVD, screenshot, read the UI hierarchy, tap/swipe/type, set a device
lock, read `logcat`, run Gradle builds and tests. [79 tools](docs/TOOLS.md),
from Claude Code, Cursor, VS Code, or any MCP client over stdio.

It is the Android counterpart to [XcodeBuildMCP](https://github.com/getsentry/XcodeBuildMCP),
built on the official [Go MCP SDK](https://github.com/modelcontextprotocol/go-sdk).

<div align="center">
<img src="assets/demo.gif" width="600" alt="An agent driving a real emulator with adb-mcp: describe_ui finds the Chrome icon, tap_on_text taps it, and a screenshot confirms Chrome launched. The emulator screen is shown side by side with the actual tool call and result.">

`describe_ui` → `tap_on_text` → `screenshot`, driven live against a real emulator (`emulator-5556`), showing the actual tool calls and their actual output.
</div>

> Android is a trademark of Google LLC. `adb-mcp` is an independent, unofficial
> tool built for Android and is not affiliated with, sponsored, or endorsed by Google.
> The Android robot above is reproduced/modified from work created and shared by
> Google and used according to terms described in the
> [Creative Commons 3.0 Attribution License](https://creativecommons.org/licenses/by/3.0/).

## Why

Driving Android by hand means a long runbook of raw `adb` commands, and it is
easy to get wrong (stale tap coordinates, CRLF-corrupted screenshots, forgetting
`exec-out`, guessing coordinates off a downscaled image). This server bakes
that knowledge into its tools, so the agent doesn't have to relearn it:

- Screenshots use `exec-out screencap` (no CRLF corruption) and are auto-downscaled
  so the image reader accepts them.
- `describe_ui` returns each element's **center in true device pixels** (so taps
  land where you mean them to, no guessing off the image) and retries the
  transient "could not get idle state" failure on its own.

The workflow itself ships as readable **resources** the agent can pull up
mid-task (the observe→act loop, native PIN/lock handling, crash triage, see
below) instead of relearning them each session.

## Getting started

### 1. Prerequisites

- Android SDK with `platform-tools` (`adb`) and `emulator`. The server finds it
  via `$ANDROID_HOME` / `$ANDROID_SDK_ROOT`, else the platform default
  (`~/Library/Android/sdk` on macOS). If your MCP client launches the server
  without those set, pass `--sdk /path/to/sdk` in the client config's `args`
  (the server then exports it, so Gradle finds the SDK too). `doctor` prints
  the location it resolved.
- At least one AVD (create one in Android Studio's Device Manager).

Go is **not** required: releases ship prebuilt binaries, and it's only needed to
[build from source](#from-source-go-126).

### 2. Install

On macOS/Linux:

```bash
curl -fsSL https://raw.githubusercontent.com/iksnerd/adb-mcp/main/install.sh | sh
```

The script ([install.sh](install.sh)) picks the right archive for your
OS/architecture, verifies its SHA-256 against the release's `checksums.txt`,
and installs to `~/.local/bin` (override with `BIN_DIR=...`; pin a version
with `VERSION=v0.17.0`).

Prefer to grab the binary yourself? Every platform's archive (macOS, Linux,
and Windows, amd64 and arm64) is on the
[Releases page](https://github.com/iksnerd/adb-mcp/releases/latest), each with a
checksum in `checksums.txt`. On Windows, download the `windows_amd64` or
`windows_arm64` zip and put `adb-mcp.exe` somewhere on your `PATH`.

Once installed, stay current with the built-in updater. It fetches the latest
release, verifies its checksum, and swaps the binary in place:

```bash
adb-mcp update
```

The registration below launches the server by the bare name `adb-mcp`, so it
must be on your `$PATH` (`which adb-mcp` should resolve; the installer warns
if `~/.local/bin` isn't on it). Otherwise point the client at the absolute
path to the binary instead.

### 3. Register with your MCP client

**Claude Code:**

```bash
claude mcp add adb -- adb-mcp
```

(When working inside this repo itself, the bundled `.mcp.json` is picked up
automatically, no registration needed.)

Or install as a **plugin**, which registers the server and adds a skill per
driving guide:

```bash
claude plugin marketplace add iksnerd/adb-mcp
claude plugin install adb-mcp@adb-mcp
```

For Codex, the same plugin ships in Codex's manifest shape:

```bash
codex plugin marketplace add iksnerd/adb-mcp
codex plugin add adb-mcp@adb-mcp-plugins
```

Either way `adb-mcp` still has to be on your `PATH` from step 2 - the plugin
registers the server, it does not install the binary.

**Cursor / VS Code**: one-click install (assumes `adb-mcp` is on your `PATH`
from step 2):

[<img src="https://cursor.com/deeplink/mcp-install-dark.svg" alt="Install in Cursor" height="20">](https://cursor.com/en/install-mcp?name=adb&config=eyJjb21tYW5kIjoiYWRiLW1jcCJ9)
[<img src="https://img.shields.io/badge/VS_Code-Install_Server-0098FF?style=flat-square" alt="Install in VS Code" height="20">](https://insiders.vscode.dev/redirect?url=vscode%3Amcp%2Finstall%3F%257B%2522name%2522%253A%2522adb%2522%252C%2522command%2522%253A%2522adb-mcp%2522%257D)

**Any other client** (Windsurf, Codex, …): run `adb-mcp` over stdio.
The usual config shape:

```json
{
  "mcpServers": {
    "adb": { "command": "adb-mcp" }
  }
}
```

To confirm it's wired up, ask your agent to "boot an emulator and take a screenshot".

### From source (Go 1.26+)

```bash
make install                 # builds ./bin/adb-mcp and copies it to ~/.local/bin
# or:
go build -o bin/adb-mcp ./cmd/adb-mcp
# or straight from the module (note the /cmd/adb-mcp suffix):
go install github.com/iksnerd/adb-mcp/cmd/adb-mcp@latest
```

## Tools

79 tools across ten areas. Every device-facing tool takes an optional
`serial` (adb `-s`). Omit it with one device attached, or pass one from
`list_devices` with several. Full reference: [docs/TOOLS.md](docs/TOOLS.md).

- **Emulator / device**: boot, list, wait-for-boot, shut down, connect over Wi-Fi, `adb_reverse` port forwarding (Metro!)
- **Observe**: `screenshot` to see (works on multi-display foldables, pick a panel with `display`), `describe_ui` for true-pixel element centers, with the focused **top window** (spot a biometric prompt, or the wrong app entirely, occluding your target via optional `package`), `filter`/`query`/`compact` modes, and a hidden-node count so absence is trustworthy
- **Interact**: tap, `tap_on_text`/`tap_element` (id-addressed), swipe, drag, long-press, type, key combos, PIN pads, `wait`, `run_sequence` (batch steps + guards in one call, which keeps native-timer flows from being perturbed by per-step round-trips); opt-in `verify_change` tells you whether a tap/key actually changed the UI; opt-in `via_accessibility` on `tap_on_text`/`tap_element` (EXPERIMENTAL) dispatches a real accessibility click for native views a coordinate tap can't reach, see [bridge/README.md](bridge/README.md)
- **Lock / Keystore / Biometrics**: set/clear a secure lock screen, check lock state, `has_biometric_enrolled` + `fingerprint_touch`/`finger_remove` to satisfy a BiometricPrompt on the emulator
- **Extended Controls (emulator)**: `send_sms` (OTP/2FA), `phone_call`, `set_battery` (also works on real devices via dumpsys), `cellular` (roaming/weak-signal/throttled), `set_sensor` (accelerometer/light/…), `rotate_screen`, `avd_snapshot`, driving the emulator's console-only panel that `describe_ui` can't see
- **App lifecycle**: install/uninstall, launch/stop, `app_state` (running pid(s) + Metro-vs-embedded bundle), `launch_dev_client` (Expo dev build → Metro, skipping the Dev Launcher), `reload_app`/`open_dev_menu`, clear data, permissions, deep links, push/pull files, `last_crash`
- **Logs & capture**: one-shot or streaming `logcat` (substring/priority/tag filters, `since` time window, opt-in `redact` to mask tokens/passwords/API keys before output), `clear_logcat`, `last_crash`, screen recording
- **Environment & diagnostics**: dark mode, mock location, clean status bar, `stay_awake` (stop a doze-happy screen blanking your screenshots), `doctor`
- **Gradle build & test**: `assembleDebug`, unit tests, instrumented tests, JVM unit-test coverage via JaCoCo (`get_coverage_report`/`get_file_coverage`), task + variant + module discovery (`list_gradle_variants`/`list_gradle_projects`), one-shot `build_and_run`
- **Session defaults**: pin `project_dir`/`serial` once (`session_set_defaults`) so a multi-module/multi-flavor project or multi-device session doesn't need them repeated on every call

The driving know-how itself ships as six MCP **resources** (`android://guide/*`)
the client can list and read. See [docs/TOOLS.md](docs/TOOLS.md) for the URIs,
or jump straight to `android://guide/driving` for the core loop below.

## The core loop

**observe → locate → act → re-observe.** `screenshot` to see, `describe_ui` to
get true-pixel centers, `tap`/`tap_on_text`/`swipe`/`input_text` to act, then
`screenshot` again to confirm. Read `android://guide/driving` for the full loop
and the gotchas that waste turns.

## Development

```bash
make check     # go vet + go test (unit tests need no emulator)
make run       # run over stdio for ma