The reputation layer for AI skills, tools & agents

CursorTouch/Android-MCP

Score: 48.0 Rank #305

MCP Server for interacting with Android Devices.

Overview

CursorTouch/Android-MCP is a Python MCP server licensed under MIT. MCP Server for interacting with Android Devices. Topics: ai, android, automation, mcp-server.

Ranked #305 out of 25632 indexed tools.

In the top 2% of all indexed tools.

Ecosystem

Python MIT
aiandroidautomationmcp-server

Signal Breakdown

Stars 450
Freshness 8d ago
Issue Health 50%
Contributors 4
Dependents 0
Forks 68
Description Brief
License MIT

How to Improve

Description low impact

Expand your description to 150+ characters for better discoverability

Dependents medium impact

No downstream dependents detected yet — adoption by other projects is the strongest trust signal

Badge

AgentRank score for CursorTouch/Android-MCP
[![AgentRank](https://agentrank-ai.com/api/badge/tool/CursorTouch--Android-MCP)](https://agentrank-ai.com/tool/CursorTouch--Android-MCP)
<a href="https://agentrank-ai.com/tool/CursorTouch--Android-MCP"><img src="https://agentrank-ai.com/api/badge/tool/CursorTouch--Android-MCP" alt="AgentRank"></a>

Matched Queries

"mcp server""mcp-server"

From the README

<div align="center">

  <h1>🤖 Android MCP</h1>

  <a href="https://github.com/CursorTouch/Android-MCP/blob/main/LICENSE">
    
  </a>
  
  
  
  <br>
  <a href="https://x.com/CursorTouch">
    
  </a>
  <a href="https://discord.com/invite/Aue9Yj2VzS">
    
  </a>

</div>

<br>

**Android-MCP** is a lightweight, open-source tool that bridge between AI agents and Android devices. Running as an MCP server, it lets LLM agents perform real-world tasks such as **app navigation, UI interaction and automated QA testing** without relying on traditional computer-vision pipelines or preprogramed scripts.

<https://github.com/user-attachments/assets/cf9a5e4e-b69f-46d4-8487-0f61a7a86d67>

## ✨ Features

- **Native Android Integration**  
  Interact with UI elements via ADB and the Android Accessibility API: launch apps, tap, swipe, input text, and read view hierarchies.

- **Bring Your Own LLM/VLM**  
  Works with any language model, no fine-tuned CV model or OCR pipeline required.

- **Rich Tools
Read full README on GitHub →
Are you the maintainer? Claim this listing