DroidMind
AI-powered control and debugging of Android devices via Model Context Protocol
Key Features
Use Cases
README
🤖 DroidMind 🧠
Control Android devices with AI through the Model Context Protocol
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), DroidMind allows AI models to directly interact with Android devices via ADB in a secure, structured way. When used as part of an agentic coding workflow, DroidMind can enable your assistant to build and debug with your device directly in the loop.
💫 Core Features
DroidMind empowers AI assistants to:
- 📱 Manage Devices: Connect via USB/TCP-IP, list devices, view properties, and reboot.
- 📊 Analyze Systems: Access logs (logcat, ANR, crash, battery), capture bug reports, and dump heap.
- 📂 Handle Files: Browse, read, write, push, pull, delete, and manage device files/directories.
- 📦 Control Apps: Install, uninstall, start, stop, clear data, and inspect app details (manifest, permissions, activities).
- 🖼️ Automate UI: Perform taps, swipes, text input, and key presses.
- 🐚 Execute Shell Commands: Run ADB shell commands with a security-conscious framework.
- 🔒 Operate Securely: Benefit from command validation, risk assessment, and sanitization.
- 💬 Integrate Seamlessly: Connect with any MCP-compatible client (Claude, Cursor, Cline, etc.).
For a detailed list of capabilities, see the User Manual and MCP Reference.
🚀 Getting Started
Quickstart for IDEs (Zero Install with uvx)
For the fastest way to integrate DroidMind with an MCP-compatible IDE (like Cursor), you can configure it to run DroidMind directly from its GitHub repository using uvx. This method does not require you to manually clone or install DroidMind first.
Add the following to your IDE's MCP configuration (e.g., .cursor/mcp.json for Cursor):
{
"mcpServers": {
"droidmind": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/hyperb1iss/droidmind",
"droidmind",
"--transport",
"stdio" // The default and preferred mode for most IDE integrations
]
}
}
}
Your IDE will be configured to launch DroidMind on demand. Full instructions for this setup are in the Quick Start Guide.
Prerequisites
- 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
For detailed instructions on setting up DroidMind, including the quick IDE integration with uvx (covered in the Quick Start), manual installation from source, or using Docker, please see our comprehensive Installation Guide.
Running DroidMind
How you run DroidMind depends on your setup:
- IDE Integration (via
uvx): Your IDE automatically manages running DroidMind as configured in its MCP settings (e.g.,mcp.json). See the Quick Start Guide. - Manual Installation: After installing from source, you can run DroidMind directly.
- Stdio (for direct terminal interaction or some IDE setups):
bash
droidmind --transport stdio - SSE (for web UIs or AI assistants like Claude Desktop):
bashThis usually starts a server at
droidmind --transport ssesse://localhost:4256/sse.
- Stdio (for direct terminal interaction or some IDE setups):
- Docker: Refer to the Docker Guide for commands to run DroidMind in a container.
Refer to the Installation Guide for more details on running DroidMind in different environments.
🐳 Running with Docker
DroidMind can also be run using Docker for a consistent, containerized environment. This is particularly useful for deployment and isolating dependencies.
For comprehensive instructions on building the Docker image and running DroidMind in a container with stdio or SSE transport, including notes on ADB device access, please refer to our Docker Guide.
🔮 Example AI Assistant Queries
With an AI assistant connected to DroidMind, you can make requests like:
- "List all connected Android devices and show their properties."
- "Take a screenshot of my Pixel."
- "Install this APK on
emulator-5554." - "Show me the recent crash logs from
your_device_serial." - "Tap the 'Next' button on the current screen of
emulator-5554."
For more inspiration, check out our Example Queries and Workflows in the User Manual.
🔒 Security
DroidMind incorporates a security framework to protect your devices:
- Command Validation & Sanitization
- Risk Assessment Categorization
- Protected Path Operations
- Comprehensive Logging
High-risk operations are flagged, and critical ones are blocked by default. Learn more in our Security Considerations chapter.
💻 Development
DroidMind uses uv for dependency management and development workflows.
# Install/update dependencies (after cloning and activating .venv)
uv pip install -e .[dev,sse]
# Run tests
pytest
# Run linting
ruff check .
# Run type checking
pyright # Ensure pyright is installed or use ruff's type checking capabilities
🤝 Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
- Fork the repository.
- Create your feature branch (
git checkout -b feature/amazing-feature). - Set up your development environment with
uv. - Make your changes.
- Run tests, linting, and type checking.
- Commit your changes (
git commit -m 'Add some amazing feature'). - Push to the branch (
git push origin feature/amazing-feature). - Open a Pull Request.
📝 License
This project is licensed under the Apache License - see the LICENSE file for details.
Created by Stefanie Jane 🌠
If you find DroidMind useful, buy me a Monster Ultra Violet ⚡️
Star History
Repository Owner
User
Repository Details
Programming Languages
Tags
Topics
Join Our Newsletter
Stay updated with the latest AI tools, news, and offers by subscribing to our weekly newsletter.
Related MCPs
Discover similar Model Context Protocol servers
JADX-AI-MCP
Automated AI-powered APK analysis via Model Context Protocol.
JADX-AI-MCP is a fully automated server and plugin for integrating Model Context Protocol (MCP) with JADX for the purpose of analyzing Android APKs using large language models such as Claude. It streamlines vulnerability discovery, reverse engineering, and static analysis by leveraging LLMs in conjunction with established tools. The project facilitates real-time code review and efficient collaboration between AI and human analysts.
- ⭐ 637
- MCP
- zinja-coder/jadx-ai-mcp
LLDB-MCP
AI-assisted debugging with LLDB via Model Context Protocol integration
LLDB-MCP enables integration of the LLDB debugger with Claude's Model Context Protocol, allowing for direct control and interaction with LLDB debugging sessions through AI. The tool offers a suite of commands for managing sessions, examining program state, and controlling execution. It facilitates natural language interaction with LLDB, streamlining tasks such as loading executables, setting breakpoints, and analyzing stack traces. Designed for seamless AI-assisted debugging workflows, LLDB-MCP enhances productivity by bridging advanced debugging capabilities with AI-driven interfaces.
- ⭐ 63
- MCP
- stass/lldb-mcp
AutoMobile
Powerful tools for mobile automation, test authoring, and device management via MCP.
AutoMobile provides a comprehensive set of tools for mobile automation, focusing on UI testing and development workflow automation. It operates as an MCP Server, enabling a robust interaction loop for model-driven actions and observations. The solution supports Android platforms with features like automated test authoring, multi-device management, and seamless CI test execution. AutoMobile also offers source mapping and deep view hierarchy analysis to enhance code rendering accuracy.
- ⭐ 63
- MCP
- zillow/auto-mobile
Mobile MCP
Platform-agnostic server for scalable mobile automation and development.
Mobile MCP is a Model Context Protocol (MCP) server that enables scalable automation and interaction with native iOS and Android devices through a unified, platform-independent API. Designed to power agents and LLMs, it supports both simulator/emulator and real device environments, allowing access via structured accessibility snapshots or coordinate-based actions. The server facilitates multi-step user journeys, data extraction, and agent-based frameworks without requiring device-specific expertise.
- ⭐ 2,436
- MCP
- mobile-next/mobile-mcp
HarmonyOS MCP Server
Enables HarmonyOS device manipulation via the Model Context Protocol.
HarmonyOS MCP Server provides an MCP-compatible server that allows programmatic control of HarmonyOS devices. It integrates with tools and frameworks such as OpenAI's openai-agents SDK and LangGraph to facilitate LLM-powered automation workflows. The server supports execution through standard interfaces and can be used with agent platforms to process natural language instructions for device actions. Its design allows for seamless interaction with HarmonyOS systems using the Model Context Protocol.
- ⭐ 25
- MCP
- XixianLiang/HarmonyOS-mcp-server
PiloTY
AI Pilot for PTY Operations via the Model Context Protocol
PiloTY is an MCP server that enables AI agents to control interactive terminals as if they were human users. It provides stateful, context-preserving terminal sessions that support interactive programs, SSH connections, and background process management. The system allows secure integration with AI platforms like Claude Code or Claude Desktop to translate natural language instructions into complex terminal workflows. Designed for extensibility and real-world development scenarios, PiloTY empowers agents to manage remote environments, debug interactively, and automate multi-step operations.
- ⭐ 12
- MCP
- yiwenlu66/PiloTY
Didn't find tool you were looking for?