Android-MCP and uiautomator2-mcp-server

These are complements that use different automation frameworks—one leverages the native Android UIAutomator while the other uses UIAutomator2—allowing users to choose based on their device compatibility and testing requirements, but they cannot be used together in the same MCP server instance.

Android-MCP
64
Established
Maintenance 10/25
Adoption 10/25
Maturity 24/25
Community 20/25
Maintenance 10/25
Adoption 3/25
Maturity 22/25
Community 12/25
Stars: 447
Forks: 67
Downloads:
Commits (30d): 0
Language: Python
License: MIT
Stars: 3
Forks: 1
Downloads:
Commits (30d): 0
Language: Python
License: Apache-2.0
No risk flags
No risk flags

About Android-MCP

CursorTouch/Android-MCP

MCP Server for interacting with Android Devices.

This tool helps quality assurance engineers, mobile app testers, and anyone needing to automate Android device interactions. It takes natural language commands and translates them into actions like app navigation, UI taps, text input, and gesture controls on Android 10+ devices. The result is automated testing, task execution, and UI interaction without manual effort or complex coding.

mobile-app-testing quality-assurance android-automation user-interface-interaction AI-agent-orchestration

About uiautomator2-mcp-server

tanbro/uiautomator2-mcp-server

A MCP (Model Context Protocol) server that provides tools for controlling and interacting with Android devices using uiautomator2.

Exposes 70+ tools for device automation (screenshots, gestures, app management, text input) via MCP protocol, with XPath-based UI element filtering to reduce token usage and tool selection controls to minimize AI hallucinations. Implements a stdio/HTTP dual-transport architecture that bridges AI assistants with Android devices through uiautomator2 and ADB, enabling conversational automation without coding. Integrates with MCP-compatible clients (Claude Desktop, Cursor) for natural language device control and includes a built-in AI-driven testing framework for UI validation.

Scores updated daily from GitHub, PyPI, and npm data. How scores work