android-mcp-server: Programmatic Android Device Control via ADB
This repository profile is provided by osrepos.com, an open source repository discovery platform.

Summary
The android-mcp-server is a Python-based Model Context Protocol (MCP) server designed to offer programmatic control over Android devices using ADB. It enables advanced device management capabilities, including screenshot capture, UI layout analysis, and package management. This server integrates seamlessly with MCP clients like Claude Desktop, providing a powerful tool for developers and automation enthusiasts.
Repository Information
Topics
Click on any tag to explore related repositories
Use at your own risk
OSRepos shares public repositories for knowledge and discovery only. Any installation, execution, configuration, or use of code from these repositories is the user's own responsibility. Always review the repository, source code, dependencies, licenses, and security implications before running or installing anything. OSRepos is not responsible for issues, damages, or losses resulting from third-party repositories.
Introduction
The android-mcp-server project provides a robust Model Context Protocol (MCP) server that facilitates programmatic control over Android devices through the Android Debug Bridge (ADB). This server exposes a range of Android device management capabilities, making it an invaluable tool for automation, testing, and development workflows. It is designed to be accessed by MCP clients, such as Claude Desktop and various code editors.
Key features include:
- ADB Command Execution
- Device Screenshot Capture
- UI Layout Analysis
- Device Package Management
Installation
To get started with android-mcp-server, follow these steps:
1. Prerequisites:
- Python 3.x
- ADB (Android Debug Bridge) installed and configured on your system.
- An Android device or emulator.
2. Clone the repository:
git clone https://github.com/minhalvp/android-mcp-server.git
cd android-mcp-server
3. Install dependencies:
This project uses uv for project management. If you don't have uv, refer to its installation guide.
uv python install 3.11
uv sync
Examples
The android-mcp-server is designed to be used with an MCP client. Here's how to configure it with Claude Desktop and an overview of the available tools.
Configuration with Claude Desktop:
- Locate your Claude Desktop configuration file:
- Windows:
%APPDATA%\Claude\claude_desktop_config.json - macOS:
~/Library/Application Support/Claude/claude_desktop_config.json
- Windows:
- Add the Android MCP server configuration to the
mcpServerssection:
{
"mcpServers": {
"android": {
"command": "path/to/uv",
"args": ["--directory", "path/to/android-mcp-server", "run", "server.py"]
}
}
}
Remember to replace path/to/uv with the actual path to your uv executable and path/to/android-mcp-server with the absolute path where you cloned the repository.
Available Tools:
The server exposes several powerful tools for interacting with Android devices:
get_packages(): Get all installed packages on the device.execute_adb_command(command: str): Executes any ADB command and returns its output.get_uilayout(): Retrieves information about clickable elements in the current UI.get_screenshot(): Takes a screenshot of the device and returns it.get_package_action_intents(package_name: str): Get all non-data actions from Activity Resolver Table for a package.
Why Use
The android-mcp-server offers a streamlined way to integrate Android device control into your development and automation workflows. By leveraging the Model Context Protocol, it allows AI agents and other clients to interact with Android devices programmatically, enabling tasks such as automated testing, UI analysis, and rapid prototyping. Its Python foundation and clear ADB integration make it accessible for developers looking to extend their control over Android environments.
Links
- GitHub Repository: minhalvp/android-mcp-server
- Model Context Protocol (MCP): Introduction
- uv Installation: Getting Started
Related repositories
Similar repositories that may be relevant next.

dify-official-plugins: Extending Dify with AI Models, Tools, and Agent Strategies
August 18, 2026
The `dify-official-plugins` repository hosts a collection of official plugins for Dify, an open-source platform for developing LLM-powered AI applications. These plugins, including models, tools, agent strategies, and extensions, enhance Dify's capabilities and are maintained by the official Dify team. They are designed to help developers efficiently build, deploy, and manage AI-driven solutions.

Agent Skills: A Standardized Way to Give AI Agents New Capabilities
August 18, 2026
Agent Skills provides a lightweight, open format for extending AI agent capabilities with specialized knowledge and workflows. It allows packaging procedural knowledge and context into portable, version-controlled folders that agents load on demand. This enables agents to gain domain expertise, follow repeatable workflows, and reuse skills across various compatible AI tools.

A-MEM: Self-Evolving Memory for Coding Agents
August 17, 2026
A-MEM is an innovative self-evolving memory system designed for coding agents, organizing knowledge into a dynamic Zettelkasten-style graph. It allows memories to evolve and connect over time, enhancing an agent's ability to recall and utilize information effectively. This system offers both semantic and structural search capabilities for a richer knowledge base.

Agent Sandbox: Secure Local Development for AI Coding Agents
August 17, 2026
Agent Sandbox provides a robust and secure local development environment specifically designed for collaborating with AI coding agents. It ensures minimal filesystem access, configurable network egress policies, and secure secret injection, protecting your local machine from potentially risky agent operations. This project supports various AI agents and integrates seamlessly with both CLI and popular IDE devcontainer setups.
Source repository
Open the original repository on GitHub.
17 counted GitHub visits