Automate Android devices using the uiautomator2 library, requiring adb and a connected device.
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.
adb
diagnostic toolPerfect for:
git clone https://github.com/nim444/mcp-android.git cd mcp-android
uv venv source .venv/bin/activate # On Windows: .venv\Scripts\activate
uv pip install
uvicorn server:app --factory --host 0.0.0.0 --port 8000
python server.py
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:
%APPDATA%\Claude\claude_desktop_config.json
~/Library/Application Support/Claude/claude_desktop_config.json
{ "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
You can also use this MCP server with VS Code's agent mode (requires VS Code 1.99 or newer). To set up:
.vscode/mcp.json
file 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:
MCP: List Servers
to view and manage configured serversMCP: Start Server
to start the serverThe project includes support for uiauto.dev, a powerful UI inspection tool for viewing and analyzing your device's interface structure.
uv pip install uiautodev
uiauto.dev
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 |
This project is licensed under the MIT License - see the LICENSE file for details.
An example of deploying a remote MCP server on Cloudflare Workers without authentication.
An MCP server for the Criage package manager, providing full client functionality via the MCP protocol.
Manage DevContainer environments using natural language prompts in any MCP-compatible editor.
A Python package with utilities and helpers for building MCP-compliant servers, often using Flask and Redis.
Connects Blender to Claude AI via the Model Context Protocol (MCP), enabling direct interaction and control for prompt-assisted 3D modeling, scene creation, and manipulation.
A Model Context Protocol (MCP) server for CODESYS V3 programming environments.
A scientific computing server for symbolic math, data analysis, and visualization using popular Python libraries like NumPy, SciPy, and Pandas.
Integrates with Microsoft's AutoGen framework to enable sophisticated multi-agent conversations via the Model Context Protocol.
Refactor code using regex-based search and replace.
Access real-time Maven Central intelligence for fast and accurate dependency information.