mcpField
A
ADB MCP Server

ADB MCP Server

Local
github.com/nhungbeoDeveloper Tools1Updated 76w ago
Repository

About ADB MCP Server

ADB MCP Server lets MCP clients inspect and operate connected Android devices through ADB. It combines device listing, screenshots, UI hierarchy extraction, and arbitrary ADB command execution.

Key features

  1. 01List connected Android devices
  2. 02Capture device screenshots
  3. 03Extract UI hierarchy as XML
  4. 04Run ADB commands on devices

Use cases

  1. 01Check which Android devices are connected
  2. 02Capture screens for debugging
  3. 03Inspect UI hierarchy for testing
  4. 04Run device-specific ADB commands

MCP support

Exposes MCP tools for listing devices, capturing screenshots, retrieving UI elements, and executing ADB commands.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

ADB MCP Server

A Model Context Protocol (MCP) server for managing Android Debug Bridge (ADB) connections and interacting with Android devices.

Features

  • Device Management: List all connected Android devices
  • Screenshot Capture: Take screenshots from connected devices
  • UI Element Inspection: Extract UI hierarchy from device screens
  • ADB Command Execution: Run arbitrary ADB commands on connected devices

Prerequisites

  • Android Debug Bridge (ADB) must be installed on your system and added to your PATH
  • Node.js (v14 or higher)
  • TypeScript

Installation

  1. Clone the repository:

    git clone https://github.com/yourusername/adb-mcp-server.git
cd adb-mcp-server

  2. Install the dependencies:

    npm install

  3. Build the project:

    npm run build

Usage

Starting the Server

The ADB MCP server runs as a Model Context Protocol server over stdio:

npm start

For development with auto-restart on file changes:

npm run dev
Available Tools

The server exposes the following MCP tools:

1. List Connected Devices
get_devices

Returns a list of all connected Android devices with their IDs and connection states.

2. Capture Screenshot
capture_screenshot

Parameters:

  • deviceId: ID of the device to capture from
  • path: Path where the screenshot will be saved

The screenshot will be named according to the format: YYYYMMDD_HH_MM_SS.png

3. Get UI Elements
get_ui_elements

Parameters:

  • deviceId: ID of the device to extract UI hierarchy from

Returns the full UI hierarchy in XML format, useful for UI automation and testing.

4. Execute ADB Command
execute_adb_command

Parameters:

  • deviceId: ID of the device to run the command on
  • command: The ADB command to execute

Allows execution of arbitrary ADB commands on the specified device.

Project Structure

adb-mcp-server
├── src
│   ├── index.ts               # Main MCP server entry point
│   ├── handlers/              # Request handlers for each feature
│   │   ├── deviceList.ts      # Device listing functionality
│   │   ├── screenshot.ts      # Screenshot capture functionality
│   │   └── uiElements.ts      # UI hierarchy extraction
│   ├── utils/                 # Utility functions
│   │   ├── adb.ts             # ADB command execution utilities
│   │   └── screenshot.ts      # Screenshot handling utilities
│   └── types/                 # TypeScript type definitions
├── package.json               # Project dependencies and scripts
└── tsconfig.json              # TypeScript configuration

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.