About Android ADB MCP Server
Android ADB MCP Server is an MCP server that lets AI assistants manage and operate Android devices through the Android Debug Bridge. It is aimed at Android developers and testers who want to automate device tasks such as installing apps, transferring files and taking screenshots.
Key features
- 01Lists and manages multiple connected devices
- 02Runs shell commands and installs or uninstalls apps
- 03Pushes and pulls files between host and device
- 04Launches apps and saves or copies screenshots
Use cases
- 01Installing APK files on a device for testing through an AI assistant
- 02Collecting screenshots and files from connected devices
- 03Automating app launches and debugging steps
MCP support
This is an MCP server that exposes ADB-based tools such as adb_devices, adb_shell, adb_install and adb_push to MCP clients.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEAndroid ADB MCP Server
A Model Context Protocol (MCP) server that enables AI assistants to interact with Android devices through the Android Debug Bridge (ADB). This server bridges the gap between AI capabilities and Android device management, allowing for seamless automation of Android development and testing operations.
⚙️ Quick Setup
Add the server to your MCP configuration file:
{
"mcpServers": {
"android-adb": {
"command": "npx",
"args": ["-y", "@landicefu/android-adb-mcp-server"],
"env": {},
"disabled": false,
"alwaysAllow": []
}
}
}
Configuration Locations
- Claude Desktop:
~/Library/Application Support/Claude/claude_desktop_config.json(macOS) - Cline/Roo Code:
~/Library/Application Support/Code/User/globalStorage/rooveterinaryinc.roo-cline/settings/cline_mcp_settings.json(macOS) - For Windows/Linux, check the equivalent application support directories
After configuring, restart your AI assistant to load the new server configuration.
📋 Prerequisites
- ADB (Android Debug Bridge) must be installed and available in your system PATH
- Install ADB on Windows, macOS, or Linux
- Verify installation by running
adb versionin your terminal
- For clipboard functionality:
- macOS:
osascript(built-in) - Windows: PowerShell (built-in)
- Linux:
xclip(install viaapt-get install xclipor equivalent)
- macOS:
- Node.js 16.x or higher
🚀 Features
- Connect to and manage multiple Android devices
- Execute shell commands on Android devices
- Install and uninstall applications
- Push and pull files between local system and Android devices
- Launch applications on Android devices
- Take screenshots and save them locally or copy to clipboard
- Smart device selection when multiple devices are connected
🛠️ Available Tools
| Tool | Description | Required Parameters | Optional Parameters |
|---|---|---|---|
adb_devices | List connected devices | None | None |
adb_shell | Execute shell commands | command | device_id |
adb_install | Install APK files | path | device_id |
adb_uninstall | Uninstall applications | package_name | device_id |
adb_list_packages | List installed packages | None | device_id, filter |
adb_pull | Pull files from device | remote_path, local_path | device_id |
adb_push | Push files to device | local_path, remote_path | device_id |
launch_app | Launch an application | package_name | device_id |
take_screenshot_and_save | Take and save screenshot | output_path | device_id, format |
take_screenshot_and_copy_to_clipboard | Take screenshot to clipboard | None | device_id, format |
Device Management
The server intelligently handles device selection:
- If only one device is connected, it will be used automatically
- If multiple devices are connected, you must specify a
device_idparameter - If no devices are connected, an error will be returned
Screenshot Path Resolution
When specifying the output_path for saving screenshots, the path is resolved as follows:
- Absolute paths are used as-is
- Paths starting with
~are expanded to the user's home directory - Relative paths are resolved relative to the user's home directory
This ensures that screenshots are saved to a location where the MCP server has write permissions.
🔍 Troubleshooting
Common Issues
-
"ADB is not available" error
- Ensure ADB is installed and in your system PATH
- Verify by running
adb versionin your terminal
-
"No Android devices connected" error
- Check if your device is properly connected with
adb devices - Ensure USB debugging is enabled on your device
- Try restarting ADB with
adb kill-serverfollowed byadb start-server
- Check if your device is properly connected with
-
"Multiple devices connected" error
- Specify the
device_idparameter in your tool call - Get the list of available devices with the
adb_devicestool
- Specify the
-
Screenshot to clipboard not working
- Ensure the required platform-specific tools are installed
🔧 Alternative Installation Methods
Option 1: Install from npm
# Install globally
npm install -g @landicefu/android-adb-mcp-server
# Or install locally in your project
npm install @landicefu/android-adb-mcp-server
Option 2: Manual Installation from Source
-
Clone the repository:
git clone https://github.com/landicefu/android-adb-mcp-server.git cd android-adb-mcp-server -
Install dependencies and build:
npm install npm run build -
Configure with direct path:
{ "mcpServers": { "android-adb": { "command": "node", "args": ["/path/to/android-adb-mcp-server/build/index.js"], "env": {}, "disabled": false, "alwaysAllow": [] } } }
📄 License
This project is licensed under the ISC License - see the LICENSE file for details.
🤝 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) - Commit your changes (
git commit -m 'Add some amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
Comments
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.