Android MCP Server logo

Android MCP Server

Community
minhalvp

An MCP server that provides control over Android devices via adb

Publisherminhalvp
Repositoryandroid-mcp-server
LanguagePython
Forks
94
Stars
811
Available tools
0
Transport typestdio
Categories
LicenseApache-2.0
Links
  • Connect tools to AI workflows

    Android MCP Server exposes MCP capabilities that can be used by compatible AI clients and agents.

  • 0 available tools

    Browse the callable actions below, including names and descriptions when provided by the server.

  • Ready-to-copy setup

    Use the installation snippets to configure this server in your preferred MCP client.

  • Open source signals

    811 stars and 94 forks from the linked repository.

Android MCP Server

An MCP (Model Context Protocol) server that provides programmatic control over Android devices through ADB (Android Debug Bridge). This server exposes various Android device management capabilities that can be accessed by MCP clients like Claude desktop and Code editors (e.g. Cursor)

Features

  • 🔧 ADB Command Execution
  • 📸 Device Screenshot Capture
  • 🎯 UI Layout Analysis
  • 📱 Device Package Management

Prerequisites

  • Python 3.x
  • ADB (Android Debug Bridge) installed and configured
  • Android device or emulator (not tested)

Installation

  1. Clone the repository:
bash
git clone https://github.com/minhalvp/android-mcp-server.git
cd android-mcp-server
  1. Install dependencies: This project uses uv for project management via various methods of installation.
bash
uv python install 3.11
uv sync

Configuration

The server supports flexible device configuration with multiple usage scenarios.

Device Selection Modes

1. Automatic Selection (Recommended for single device)

  • No configuration file needed
  • Automatically connects to the only connected device
  • Perfect for development with a single test device

2. Manual Device Selection

  • Use when you have multiple devices connected
  • Specify exact device in configuration file

Configuration File (Optional)

The configuration file (config.yaml) is optional. If not present, the server will automatically select the device if only one is connected.

For Automatic Selection

Simply ensure only one device is connected and run the server - no configuration needed!

For Manual Selection

  1. Create a configuration file:
bash
cp config.yaml.example config.yaml
  1. Edit config.yaml and specify your device:
yaml
device:
  name: "your-device-serial-here" # Device identifier from 'adb devices'

For auto-selection, you can use any of these methods:

yaml
device:
  name: null              # Explicit null (recommended)
  # name: ""              # Empty string  
  # name:                 # Or leave empty/comment out

Finding Your Device Serial

To find your device identifier, run:

bash
adb devices

Example output:

List of devices attached
13b22d7f        device
emulator-5554   device

Use the first column value (e.g., 13b22d7f or emulator-5554) as the device name.

Usage Scenarios

ScenarioConfiguration RequiredBehavior
Single device connectedNone✅ Auto-connects to the device
Multiple devices, want specific oneconfig.yaml with device.name✅ Connects to specified device
Multiple devices, no configNone❌ Shows error with available devices
No devices connectedN/A❌ Shows "no devices" error

Note: If you have multiple devices connected and don't specify which one to use, the server will show an error message listing all available devices.

Usage

An MCP client is needed to use this server. The Claude Desktop app is an example of an MCP client. To use this server with Claude Desktop:

  1. Locate your Claude Desktop configuration file:

    • Windows: %APPDATA%\Claude\claude_desktop_config.json
    • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  2. Add the Android MCP server configuration to the mcpServers section:

json
{
  "mcpServers": {
    "android": {
      "command": "path/to/uv",
      "args": ["--directory", "path/to/android-mcp-server", "run", "server.py"]
    }
  }
}

Replace:

  • path/to/uv with the actual path to your uv executable
  • path/to/android-mcp-server with the absolute path to where you cloned this repository

https://github.com/user-attachments/assets/c45bbc17-f698-43e7-85b4-f1b39b8326a8

Available Tools

The server exposes the following tools:

python
def get_packages() -> str:
    """
    Get all installed packages on the device.
    Returns:
        str: A list of all installed packages on the device as a string
    """
python
def execute_adb_command(command: str) -> str:
    """
    Executes an ADB command and returns the output.
    Args:
        command (str): The ADB command to execute
    Returns:
        str: The output of the ADB command
    """
python
def get_uilayout() -> str:
    """
    Retrieves information about clickable elements in the current UI.
    Returns a formatted string containing details about each clickable element,
    including their text, content description, bounds, and center coordinates.

    Returns:
        str: A formatted list of clickable elements with their properties
    """
python
def get_screenshot() -> Image:
    """
    Takes a screenshot of the device and returns it.
    Returns:
        Image: the screenshot
    """
python
def get_package_action_intents(package_name: str) -> list[str]:
    """
    Get all non-data actions from Activity Resolver Table for a package
    Args:
        package_name (str): The name of the package to get actions for
    Returns:
        list[str]: A list of all non-data actions from the Activity Resolver
        Table for the package
    """

Contributing

Contributions are welcome!

Acknowledgments

Installation

TypingMind
{
  "mcpServers": {
    "minhalvp-android-mcp-server": {
      "command": "uv",
      "args": [
        "--directory",
        "path/to/android-mcp-server",
        "run",
        "server.py"
      ]
    }
  }
}

Use Android MCP Server MCP with multiple AI models

TypingMind connects MCP tools at the workspace level, so once Android MCP Server is connected, you can use it with different AI models in TypingMind instead of setting it up separately for each model. This MCP runs locally through the TypingMind MCP connector on your device.

Setup guide to use the local connector

Use this when the MCP server needs access to local files, apps, or private resources on your computer.

1

Open the MCP settings

In TypingMind, go to Settings, Advanced Settings, then Model Context Protocol and choose Setup Connector.

  1. Open TypingMind in your browser.
  2. Click the Settings icon.
  3. Go to Advanced Settings.
  4. Open the Model Context Protocol section.
  5. Click Setup Connector and choose This Device.
TypingMind MCP connector setup screen with This Device selected
2

Run the connector command

Choose This Device, copy the command from TypingMind, and run it in Terminal. Keep the process running while you use MCP.

  1. Copy the setup command shown by TypingMind.
  2. Open Terminal on macOS or Windows Terminal on Windows.
  3. Paste and run the command.
  4. Approve the package install if Terminal asks you to proceed.
  5. Keep the Terminal window running while using MCP tools.
3

Add Android MCP Server as a server

When the connector status is Ready, click Edit Servers and paste the MCP server configuration.

  1. Wait until the connector status shows Ready.
  2. Click Edit Servers.
  3. Paste the Android MCP Server MCP server configuration.
  4. Save the server list.
  5. Refresh if you want to confirm the connector is still ready.
TypingMind MCP settings showing active server and Edit Servers button
{
  "mcpServers": {
    "minhalvp-android-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "<mcp-server-package>"
      ]
    }
  }
}
4

Use it across models

Save the server list, open Plugins, enable the Android MCP Server MCP tools, then select any supported AI model in TypingMind and use the tools in chat or assign them to an AI agent.

  1. Open the Plugins page in TypingMind.
  2. Enable the Android MCP Server MCP tools.
  3. Start a chat and choose the AI model you want to use.
  4. Use the MCP tools in chat or assign them to an AI agent.
  5. Switch to another AI model whenever needed without reconnecting MCP.
TypingMind chat using enabled MCP tools with a selected AI model
Can you use Android MCP Server to help me with this task?
Android MCP Server
Sure. I read it.
Here is what I found using Android MCP Server.

Frequently asked questions

What is the Android MCP Server MCP server used for?

Android MCP Server is an MCP server that lets compatible AI clients connect to external tools and context. In TypingMind, you can add this MCP server once and make its tools available in your AI workspace.

Can I use Android MCP Server MCP with multiple AI models in TypingMind?

Yes. TypingMind connects MCP tools at the workspace level, so you can use Android MCP Server with different AI models such as Claude, ChatGPT, Gemini, or other models you have configured in TypingMind without setting up the MCP server separately for each model.

Why use Android MCP Server MCP with TypingMind?

TypingMind is one of the best frontends for LLM chat because it brings multiple AI models, prompts, plugins, AI agents, API keys, and MCP tools into one workspace. With Android MCP Server connected, you can use its MCP tools across your preferred models while keeping your chat workflow organized in TypingMind.

How do I connect Android MCP Server MCP to TypingMind?

Android MCP Server runs through the TypingMind local MCP connector. This is best when the MCP server needs access to local files, desktop apps, command-line tools, or private resources on your computer.

What tools does Android MCP Server MCP provide in TypingMind?

Android MCP Server exposes MCP capabilities that can be enabled from the TypingMind Plugins page and used in chat or assigned to AI agents.

Do I need to share my API keys with TypingMind to use Android MCP Server MCP?

No. TypingMind is local-first and lets you keep your model providers, API keys, prompts, and MCP configuration under your control. If Android MCP Server requires authentication, add the required headers, OAuth settings, or local configuration for that MCP server when you create the connection.

Related MCP Servers

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇