Beeper MCP Server

Beeper MCP Server

Provides read-only access to local Beeper message history on macOS, enabling users to search conversations, read messages, and list recent chats through natural language queries. Supports both SQLite and IndexedDB storage formats with privacy-focused local-only operation.

Category
访问服务器

README

Beeper MCP Server

A Model Context Protocol (MCP) server that provides read-only access to Beeper messages on macOS. This server allows Claude Desktop and other MCP clients to search and read your local Beeper message history.

Features

  • Read-only access to local Beeper SQLite and IndexedDB (LevelDB) databases
  • Auto-discovery of Beeper databases in common macOS locations
  • Dual storage format support: SQLite and IndexedDB/LevelDB
  • Cross-version compatibility with different Beeper/Element database schemas
  • Three MCP tools:
    • list_conversations: View recent conversations with metadata
    • read_messages: Read messages from specific conversations
    • search_messages: Search across all message content
  • Privacy-focused: No network requests, no data persistence, local-only operation
  • Security: SQL injection protection, read-only database connections

Quick Start

Prerequisites

  • Python 3.8 or higher
  • Beeper desktop app installed on macOS
  • Claude Desktop (for integration)
  • For IndexedDB support: LevelDB libraries (install with brew install leveldb)

Installation

  1. Clone this repository:
git clone https://github.com/yourusername/beeper-mcp-server.git
cd beeper-mcp-server
  1. Install dependencies:
pip install -r requirements.txt
  1. Test the server:
python main.py

The server should start and display: Starting Beeper MCP server...

Press Ctrl+C to stop.

Claude Desktop Integration

  1. Open Claude Desktop settings
  2. Navigate to Developer → Model Context Protocol
  3. Add a new MCP server with the following configuration:
{
  "beeper": {
    "command": "python",
    "args": ["/path/to/beeper-mcp-server/main.py"]
  }
}

Replace /path/to/beeper-mcp-server with the actual path where you cloned this repository.

  1. Restart Claude Desktop
  2. Look for the 🔌 icon to confirm the server is connected

Usage Examples

Once integrated with Claude Desktop, you can use these commands:

List Recent Conversations

Ask Claude: "Use the beeper tool to list my recent conversations"

Read Messages from a Conversation

Ask Claude: "Read the last 20 messages from conversation [conversation_id]"

Search Messages

Ask Claude: "Search my Beeper messages for 'meeting tomorrow'"

Configuration

The server uses config.json for configuration. Default settings:

{
  "database_paths": [
    "~/Library/Application Support/Beeper",
    "~/Library/Application Support/Beeper/IndexedDB",
    "~/.config/Beeper",
    "~/Library/Application Support/Element",
    "~/.config/Element"
  ],
  "max_results": 50,
  "log_level": "INFO"
}

Custom Database Paths

If Beeper is installed in a non-standard location, add the path to database_paths in config.json.

Environment Variables

You can also set database paths via environment variable:

export BEEPER_DB_PATH="/custom/path/to/beeper"
python main.py

Troubleshooting

Server won't start

  • Ensure Python 3.8+ is installed: python --version
  • Check that all dependencies are installed: pip install -r requirements.txt
  • Verify the file has execute permissions: chmod +x main.py

No conversations found

  • Ensure Beeper desktop app has been used and has message history
  • Check that Beeper is installed in one of the default locations
  • Try adding your Beeper installation path to config.json
  • Check logs for database discovery details
  • For IndexedDB: Look for .indexeddb.leveldb directories in Application Support

Permission errors

  • The server only needs read access to Beeper databases
  • On macOS, you may need to grant terminal/Python disk access in System Preferences → Security & Privacy

Database not found

Run the test script to check database discovery:

python test_server.py

Testing

Run the included test utilities:

# Test database discovery
python test_server.py --discover

# Test with sample data
python test_server.py --sample

# Full integration test
python test_server.py --full

Security Notes

  • Read-only: All database connections are read-only
  • Local only: No network requests or external communication
  • No persistence: No data is cached or stored
  • Input validation: All user inputs are validated and parameterized
  • SQL injection protection: Uses parameterized queries throughout

Development

Project Structure

beeper-mcp-server/
├── main.py              # MCP server entry point
├── beeper_reader.py     # Database access logic
├── requirements.txt     # Python dependencies
├── config.json         # Configuration
├── README.md           # This file
└── test_server.py      # Testing utilities

Adding New Features

  1. Database queries: Add to beeper_reader.py
  2. New MCP tools: Register in main.py
  3. Configuration options: Update config.json and _load_config()

Debugging

Enable debug logging:

{
  "log_level": "DEBUG"
}

Or via command line:

python main.py --debug

Known Limitations

  • macOS only (uses macOS-specific paths)
  • Read-only access (by design)
  • Limited to local Beeper installations
  • Message formatting may vary by Beeper version
  • IndexedDB support requires plyvel library and system LevelDB installation

Contributing

Pull requests welcome! Please:

  • Maintain read-only operation
  • Add tests for new features
  • Update documentation
  • Follow existing code style

License

MIT License - see LICENSE file for details

Support

For issues or questions:

  • Check troubleshooting section above
  • Review debug logs
  • Open an issue on GitHub

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选