MCP Android Agent
Automate Android devices using the uiautomator2 library, requiring adb and a connected device.
MCP Android Agent
This project provides an MCP (Model Context Protocol) server for automating Android devices using uiautomator2. It's designed to be easily plugged into AI agents like GitHub Copilot Chat, Claude, or Open Interpreter to control Android devices through natural language.
Quick Demo
Requirements
- Python 3.13 or higher
- Android Debug Bridge (adb) installed and in PATH
- Connected Android device with USB debugging enabled
- uiautomator2 compatible Android device
Features
- Start, stop, and manage apps by package name
- Retrieve installed apps and current foreground app
- Tap, swipe, scroll, drag, and perform UI interactions
- Get device info, screen resolution, battery status, and more
- Capture screenshots or last toast messages
- Programmatically unlock, wake, or sleep the screen
- Clear app data and wait for activities
- Includes a health check and
adbdiagnostic tool
Use Cases
Perfect for:
- AI agents that need to interact with real devices
- Remote device control setups
- Automated QA tools
- Android bot frameworks
- UI testing and automation
- Device management and monitoring
Installation
1. Clone the repo
git clone https://github.com/nim444/mcp-android.git cd mcp-android
2. Create and activate virtual environment
Using uv (https://github.com/astral-sh/uv)
uv venv source .venv/bin/activate # On Windows: .venv\Scripts\activate
3. Install dependencies
uv pip install
Running the Server
Option 1: Using uvicorn (Recommended)
uvicorn server:app --factory --host 0.0.0.0 --port 8000
Option 2: Using MCP stdio (For AI agent integration)
python server.py
Usage
An MCP client is needed to use this server. The Claude Desktop app is an example of an MCP client. To use this server 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
Add the Android MCP server configuration to the mcpServers section
{ "mcpServers": { "mcp-android": { "type": "stdio", "command": "bash", "args": [ "-c", "cd /path/to/mcp-adb && source .venv/bin/activate && python -m server" ] } } }
Replace /path/to/mcp-adb with the absolute path to where you cloned this repository. For example: /Users/username/Projects/mcp-adb
Using with VS Code
You can also use this MCP server with VS Code's agent mode (requires VS Code 1.99 or newer). To set up:
- Create a
.vscode/mcp.jsonfile in your workspace:
{ "servers": { "mcp-android": { "type": "stdio", "command": "bash", "args": [ "-c", "cd /path/to/mcp-adb && source .venv/bin/activate && python -m server" ] } } }
Replace /path/to/mcp-adb with the absolute path to where you cloned this repository.
After adding the configuration, you can manage the server using:
- Command Palette →
MCP: List Serversto view and manage configured servers - Command Palette →
MCP: Start Serverto start the server - The server's tools will be available in VS Code's agent mode chat
UI Inspector
The project includes support for uiauto.dev, a powerful UI inspection tool for viewing and analyzing your device's interface structure.
- Install the UI inspector:
uv pip install uiautodev
- Start the inspector:
uiauto.dev
- Open your browser and navigate to https://uiauto.dev
Available MCP Tools
| Tool Name | Description |
|---|---|
| mcp_health | Check if the MCP server is running properly |
| connect_device | Connect to an Android device and get basic info |
| get_installed_apps | List all installed apps with version and package info |
| get_current_app | Get info about the app currently in the foreground |
| start_app | Start an app by its package name |
| stop_app | Stop an app by its package name |
| stop_all_apps | Stop all currently running apps |
| screen_on | Turn on the screen |
| screen_off | Turn off the screen |
| get_device_info | Get detailed device info: serial, resolution, battery, etc. |
| press_key | Simulate hardware key press (e.g. home, back, menu, etc.) |
| unlock_screen | Unlock the screen (turn on and swipe if necessary) |
| check_adb | Check if ADB is installed and list connected devices |
| wait_for_screen_on | Wait asynchronously until the screen is turned on |
| click | Tap on an element by text, resourceId, or description |
| long_click | Perform a long click on an element |
| send_text | Input text into currently focused field (optionally clearing before) |
| get_element_info | Get info on UI elements (text, bounds, clickable, etc.) |
| swipe | Swipe from one coordinate to another |
| wait_for_element | Wait for an element to appear on screen |
| screenshot | Take and save a screenshot from the device |
| scroll_to | Scroll until a given element becomes visible |
| drag | Drag an element to a specific screen location |
| get_toast | Get the last toast message shown on screen |
| clear_app_data | Clear user data/cache of a specified app |
| wait_activity | Wait until a specific activity appears |
| dump_hierarchy | Dump the UI hierarchy of the current screen as XML |
License
This project is licensed under the MIT License - see the LICENSE file for details.
Related Servers
pyATS
Interact with network devices using Cisco's pyATS and Genie libraries for model-driven automation.
ASKME-CLI
A command-line interface to prompt users for their next plan or confirmation.
LAML MCP Server
Loads and validates LAML (YAML-based markup language) documents via the Model Context Protocol.
Cloudflare MCP Server Example
A template for deploying a remote MCP server on Cloudflare Workers without authentication.
BlenderMCP
Connects Blender to Claude AI via the Model Context Protocol (MCP), enabling direct AI interaction for prompt-assisted 3D modeling, scene creation, and manipulation.
Lilith Shell
Execute terminal commands through a secure shell interface using an AI assistant.
Ollama MCP Bridge
A bridge API service connecting Ollama with Model Context Protocol (MCP) servers.
MCP Server + Asgardeo
A sample MCP server that uses Asgardeo for client authentication and connection.
CodeRabbit
Integrate with CodeRabbit AI for automated code reviews, pull request analysis, and report generation.
MCP HAR Server
Parses HAR (HTTP Archive) files and displays requests in a simplified format for AI assistants.