adb-mcp and agent-droid-bridge

These two tools are complements because they both implement the MCP server protocol for controlling Android devices via ADB, with `srmorete/adb-mcp` providing a general TypeScript implementation and `Neverlow512/agent-droid-bridge` leveraging it to offer AI agents programmatic control.

adb-mcp
51
Established
agent-droid-bridge
36
Emerging
Maintenance 2/25
Adoption 7/25
Maturity 25/25
Community 17/25
Maintenance 13/25
Adoption 5/25
Maturity 18/25
Community 0/25
Stars: 37
Forks: 10
Downloads:
Commits (30d): 0
Language: JavaScript
License: MIT
Stars: 14
Forks:
Downloads:
Commits (30d): 0
Language: Python
License: MIT
Stale 6m
No risk flags

About adb-mcp

srmorete/adb-mcp

An MCP (Model Context Protocol) server for interacting with Android devices through ADB in TypeScript.

This tool helps AI models interact with Android devices by translating complex device operations into simple instructions. It takes an AI model's requests (like 'install app' or 'take screenshot') and executes them on a connected Android phone or emulator. This is for AI developers building or testing applications that need to automate interactions with Android devices, such as for testing, data collection, or research.

Android-automation AI-testing device-interaction mobile-app-development AI-driven-UI-analysis

About agent-droid-bridge

Neverlow512/agent-droid-bridge

Agent Droid Bridge gives AI agents programmatic control over Android devices and emulators via ADB, exposed as an MCP server.

This helps mobile app developers, QA engineers, and security researchers automate complex interactions with Android devices and emulators. It allows an AI agent to control a device by sending commands like tapping the screen, typing text, launching apps, and even executing arbitrary ADB commands. The AI agent receives structured feedback on the device's state, enabling sophisticated automated workflows for testing, analysis, and reverse engineering.

mobile-app-testing android-automation app-security-analysis mobile-device-management app-reverse-engineering

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