Bookmark Manager MCP
A Model Context Protocol server that provides persistent storage, categorization, and retrieval of bookmarks through AI clients like Claude. It allows users to manage web links using custom categories and includes options for local JSON storage or AWS S3 synchronization.
README
🔖 Bookmark Manager MCP
A Model Context Protocol (MCP) server for managing bookmarks with persistent storage
<img src="image/README/1753001290532.png" width="400" alt="Bookmark Manager MCP">
📋 Overview
This MCP server provides a simple yet powerful bookmark management system that integrates seamlessly with Claude and other MCP-compatible clients. It offers persistent storage, categorization, and easy retrieval of your bookmarks.
✨ Features
- 📁 Persistent Storage: Bookmarks are saved to
~/.data/bookmarks.json - 🏷️ Categories: Organize bookmarks with custom categories
- 🔍 Resource Discovery: Browse bookmarks by category using MCP resources
- 🐳 Container Support: Ready-to-use container image (Docker/Podman)
- ⚡ TypeScript: Type-safe implementation with Zod validation
- 🔗 MCP Integration: Full Model Context Protocol compliance
🛠️ Installation
🔧 Claude Code Integration
# Add to Claude Code (Docker)
docker pull mindriftfall2infinitepiio/bookmark-manager-mcp:latest
claude mcp add bookmark-manager -- docker run \
--rm \
--interactive \
--volume ~/.data:/app/.data \
mindriftfall2infinitepiio/bookmark-manager-mcp:latest
# Or with Podman
podman pull mindriftfall2infinitepiio/bookmark-manager-mcp:latest
claude mcp add bookmark-manager -- podman run \
--rm \
--interactive \
--volume ~/.data:/app/.data \
mindriftfall2infinitepiio/bookmark-manager-mcp:latest
🔧 VS Code Integration
# Docker
docker pull mindriftfall2infinitepiio/bookmark-manager-mcp:latest
# Or Podman
podman pull mindriftfall2infinitepiio/bookmark-manager-mcp:latest
- Create
.vscode/mcp.json
{
"servers": {
"bookmark-manager": {
"command": "docker",
"args": [
"run",
"--rm",
"--interactive",
"--volume",
"~/.data:/app/.data",
"mindriftfall2infinitepiio/bookmark-manager-mcp:latest"
]
}
}
}
For Podman users:
{
"servers": {
"bookmark-manager": {
"command": "podman",
"args": [
"run",
"--rm",
"--interactive",
"--volume",
"~/.data:/app/.data",
"mindriftfall2infinitepiio/bookmark-manager-mcp:latest"
]
}
}
}
Local Development
# Clone the repository
git clone https://github.com/infinitepi-io/bookmark-manager-mcp.git
cd bookmark-manager-mcp
# Install dependencies
pnpm install
# Development mode
pnpm run dev
# Build for production
pnpm run build
pnpm start
🚀 Usage
GitHub Copilot (VS Code)
Agent Mode + Natural Language or # prefix
Add bookmark for GitHub at https://github.com category development
#add bookmark: title "GitHub", url "https://github.com"
#list all my bookmarks in development category
Claude Code (CLI)
Usage: @ prefix
claude @bookmark-manager add bookmark for GitHub at https://github.com
claude @bookmark-manager search development bookmarks
claude @bookmark-manager list all bookmarks
MCP Resources Available
bookmarks://all- All bookmarksbookmarks://mcp- MCP-related bookmarksbookmarks://general- General bookmarksbookmarks://{category}- Custom category bookmarks
Example Usage with Claude
Add a bookmark for "OpenAI Documentation" with URL "https://docs.openai.com" in category "ai"
List all my bookmarks
Show me all MCP-related bookmarks
💾 Data Storage
Storage Location
- Local:
~/.data/bookmarks.json - Container (Docker/Podman):
/app/.data/bookmarks.json(mount your local~/.datadirectory)
Data Format
[
{
"title": "Model Context Protocol",
"url": "https://modelcontextprotocol.io/introduction",
"category": "mcp"
},
{
"title": "infinitepi-io",
"url": "https://github.com/infinitepi-io",
"category": "general"
}
]
Data Persistence
- Automatic Creation: If no bookmarks file exists, default bookmarks are created
- Error Handling: Graceful error handling for file operations
- Backup Strategy: Simple JSON format allows easy backup and restoration
🐳 Container Configuration
Image Details
- Base Image:
node:22-alpine - Size: Optimized for minimal footprint
- Volumes:
/app/.datafor persistent storage
📊 Technical Details
Dependencies
- @modelcontextprotocol/sdk: ^1.13.2
- zod: ^3.25.67 (Schema validation)
- Node.js: 22+
- TypeScript: 5.0+
Build Process
# TypeScript compilation with esbuild
esbuild index.ts --bundle --platform=node --target=node22 --format=esm --outfile=dist/index.js
Architecture
┌─────────────────┐ ┌─────────────────┐ ┌─────────────────┐
│ MCP Client │◄──►│ MCP Server │◄──►│ JSON Storage │
│ (Claude) │ │ (This App) │ │ (~/.data/) │
└─────────────────┘ └─────────────────┘ └─────────────────┘
Synching your bookmark to S3 or vice versa BYOS3(Bring your own s3 on aws)
- Use below function to copy the data from local to s3 or s3 to local:
🤝 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
📝 License
This project is licensed under the Apache License 2.0.
👤 Author
Satish Tripathi
- GitHub: @infinitepi-io
- Blog: https://dev.to/mindriftfall2infinitepiio/building-a-bookmark-manager-with-ai-integration-my-journey-with-model-context-protocol-2j32
🆘 Support
- Issues: GitHub Issues
- Documentation: MCP Documentation
- Container Registry: mindriftfall2infinitepiio/mcp
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。
