ScoutlyMCP
Enables AI assistants to retrieve SMS messages from Android devices via ADB.
README
ScoutlyMCP
ScoutlyMCP is a Model Context Protocol (MCP) server that enables AI assistants to retrieve SMS messages from Android devices via ADB (Android Debug Bridge). This tool bridges your Android SMS inbox with AI assistants, allowing them to read and analyze your text messages when needed.
Features
- 🔍 SMS Retrieval: Fetch latest SMS messages from Android devices
- 🤖 MCP Integration: Compatible with MCP-enabled AI assistants
- 📱 ADB-based: Uses Android Debug Bridge for secure device communication
- ⚡ Fast Processing: Efficiently parses and formats SMS data
- 📊 Structured Output: Returns well-formatted JSON data with timestamps
Prerequisites
- Python 3.12 or higher
- Android Debug Bridge (ADB) installed and accessible in PATH
- Android device with USB debugging enabled
- Connected Android device via USB
Installing ADB
Ubuntu/Debian:
sudo apt install android-tools-adb
macOS:
brew install android-platform-tools
Windows: Download from Android SDK Platform Tools
Installation
-
Clone the repository:
git clone https://github.com/rexrk/ScoutlyMCP.git cd ScoutlyMCP -
Install dependencies:
pip install -e .
Setup
Android Device Configuration
-
Enable Developer Options:
- Go to Settings → About Phone
- Tap "Build Number" 7 times
-
Enable USB Debugging:
- Go to Settings → Developer Options
- Enable "USB Debugging"
-
Connect and Verify:
adb devicesYour device should appear in the list.
Usage
Standalone Usage
Run the SMS parser directly:
python src/message_parser.py
As MCP Server
Start the MCP server:
python src/main.py
The server will run in stdio mode, ready to receive MCP requests.
MCP Tool Usage
The server exposes one tool:
sms_message: Retrieve latest SMS messages- Parameter:
limit(optional, default: 5) - Number of messages to retrieve
- Parameter:
Example Output
[
{
"id": "123",
"address": "+1234567890",
"date": "2024-01-15T10:30:45.000Z",
"body": "Hello! This is a sample SMS message."
},
{
"id": "122",
"address": "contact@example.com",
"date": "2024-01-15T09:15:30.000Z",
"body": "Another message example with multiple lines\nThis continues on the next line."
}
]
Integration with AI Assistants
Claude Desktop
Add to your Claude Desktop MCP configuration:
{
"mcpServers": {
"sms-reader": {
"command": "uv",
"args": [
"run",
"--directory",
"/absolute/path/to/ScoutlyMCP",
"-m",
"src.main"
]
}
}
}
Project Structure
ScoutlyMCP/
├── src/
│ ├── __init__.py
│ ├── main.py # MCP server entry point
│ └── message_parser.py # SMS parsing logic
├── pyproject.toml # Project dependencies
├── README.md
└── uv.lock # Lock file for dependencies
Development
Running Tests
# Test SMS parsing functionality
python src/message_parser.py
Contributing
- Fork the repository
- Create your feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'Add some amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
Security Considerations
- Device Access: This tool requires ADB access to your Android device
- SMS Privacy: Only use with trusted AI assistants and secure environments
- Network Security: Ensure your development environment is secure
- Permissions: The tool only reads SMS data, it cannot send messages
Troubleshooting
Common Issues
ADB not found:
Error: ADB not found. Please ensure it is installed and in your system's PATH.
→ Install ADB and add to PATH
Device not connected:
Error executing ADB command
→ Check USB connection and enable USB debugging
No SMS data:
- Verify device has SMS messages in inbox
- Check ADB permissions on device
- Ensure device is unlocked during operation
License
This project is licensed under the MIT License - see the LICENSE file for details.
Acknowledgments
- Built using FastMCP
- Android Debug Bridge by Google
- Model Context Protocol specification
Support
If you encounter any issues or have questions:
- Open an Issue
- Check existing Discussions
Note: Remember to replace yourusername with your actual GitHub username when uploading to GitHub.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。