Back to MCP Catalog

DroidMind MCP Server

Developer ToolsPython
Control Android devices with AI using natural language commands
Available Tools

device_list

List all connected Android devices

format

device_properties

Get properties of a specific Android device

device_serialproperty

device_reboot

Reboot an Android device

device_serialmode

screenshot

Take a screenshot of an Android device

device_serialoutput_path

app_install

Install an application on an Android device

device_serialapk_path

app_uninstall

Uninstall an application from an Android device

device_serialpackage_name

app_list

List installed applications on an Android device

device_serialfilter

file_list

List files and directories on an Android device

device_serialpath

file_read

Read a file from an Android device

device_serialpath

file_write

Write content to a file on an Android device

device_serialpathcontent

ui_tap

Tap at specific coordinates on the device screen

device_serialxy

ui_swipe

Perform a swipe gesture on the device screen

device_serialstart_xstart_yend_xend_yduration

ui_text

Input text on the device

device_serialtext

logcat

View device logs (logcat)

device_serialfilterformat

shell_exec

Execute a shell command on the device

device_serialcommand

DroidMind is a powerful bridge between AI assistants and Android devices, enabling control, debugging, and system analysis through natural language. By implementing the Model Context Protocol (MCP), it allows AI models to directly interact with Android devices via ADB in a secure, structured way. With DroidMind, AI assistants can manage devices, analyze system logs, handle files, control applications, automate UI interactions, and execute shell commands. This makes it an invaluable tool for developers working on Android applications, allowing them to integrate device testing and debugging directly into their AI-assisted workflows.

Overview

DroidMind enables AI assistants to control and interact with Android devices through natural language commands. It serves as a bridge between AI models and Android Debug Bridge (ADB), allowing for seamless device management, app control, file operations, and UI automation.

Prerequisites

Before installing DroidMind, ensure you have:

  • Python 3.13 or higher
  • uv (Python package manager)
  • Android device with USB debugging enabled
  • ADB (Android Debug Bridge) installed and in your system's PATH

Installation Options

Option 1: IDE Integration with uvx (Recommended)

The fastest way to use DroidMind is to configure your MCP-compatible IDE (like Cursor) to run it directly from GitHub:

  1. Add the DroidMind configuration to your IDE's MCP settings file (e.g., .cursor/mcp.json for Cursor)
  2. Your IDE will automatically manage running DroidMind when needed

Option 2: Manual Installation

If you prefer to install DroidMind locally:

  1. Clone the repository: git clone https://github.com/hyperb1iss/droidmind.git
  2. Navigate to the directory: cd droidmind
  3. Install with uv: uv pip install -e .

Option 3: Docker

For a containerized environment:

  1. Build the Docker image: docker build -t droidmind .
  2. Run the container with appropriate device access

Running DroidMind

How you run DroidMind depends on your setup:

  • IDE Integration: Your IDE handles this automatically based on your MCP configuration
  • Manual Installation:
    • For terminal/IDE integration: droidmind --transport stdio
    • For web UIs or Claude Desktop: droidmind --transport sse
  • Docker: Use appropriate Docker commands with device access flags

Usage Examples

Once connected to an AI assistant, you can make requests like:

  • "List all connected Android devices and show their properties"
  • "Take a screenshot of my device"
  • "Install this APK on the emulator"
  • "Show me the recent crash logs"
  • "Tap the 'Next' button on the current screen"
  • "Check the battery status of my device"

Security Features

DroidMind includes several security measures:

  • Command validation and sanitization
  • Risk assessment categorization
  • Protected path operations
  • Comprehensive logging

High-risk operations are clearly identified, and the system is designed to prevent potentially harmful actions.

Troubleshooting

If you encounter issues:

  1. Ensure ADB is properly installed and in your PATH
  2. Verify USB debugging is enabled on your Android device
  3. Check that your device is properly connected and authorized
  4. Review the DroidMind logs for specific error messages

For more detailed information, refer to the official documentation.

Related MCPs

Apple Shortcuts
Developer ToolsJavaScript

Control Apple Shortcuts automations from AI assistants

Clojars Dependency Lookup
Developer ToolsJavaScript

Fetch dependency information from Clojars, the Clojure community's artifact repository

Simple Timeserver
Developer ToolsPython

Provides Claude with current time and timezone information

About Model Context Protocol

Model Context Protocol (MCP) allows AI models to access external tools and services, extending their capabilities beyond their training data.

Generate Cursor Documentation

Save time on coding by generating custom documentation and prompts for Cursor IDE.