Raindrop.io

🚀 Raindrop.io MCP Server

This project provides a Model Context Protocol (MCP) server for interacting with the Raindrop.io bookmarking service. It enables large language models (LLMs) and other AI agents to access and manage your Raindrop.io data via the MCP standard.

✨ Features

• CRUD Operations: Create, read, update, and delete collections and bookmarks.
• Advanced Search: Filter bookmarks by tags, domains, types, creation dates, etc.
• Tag Management: List, rename, merge, and delete tags.
• Highlight Access: Retrieve text highlights in bookmarks.
• Collection Management: Reorder, expand/collapse, merge, and delete empty collections.
• File Upload: Upload files directly to Raindrop.io.
• Reminder Setting: Set reminders for specific bookmarks.
• Import/Export: Initiate and check the status of bookmark imports and exports.
• Recycle Bin Management: Empty the recycle bin.
• MCP Compliance: Expose Raindrop.io features through MCP resources and tools.
• Streaming Support: Provide a real - time SSE (Server - Sent Events) endpoint for streaming bookmark updates.
• TypeScript Usage: Strong typing for better maintainability.
• Axios Usage: Send requests to the Raindrop.io API.
• Zod Usage: Perform robust schema validation on API parameters and responses.
• MCP SDK Usage: Leverage the official @modelcontextprotocol/sdk.

📦 Installation

Prerequisites

• Node.js (v18 or higher)
• Bun environment

Steps

1. Clone the repository:

   git clone https://github.com/yourusername/raindrop-mcp-server.git
   cd raindrop-mcp-server
   

2. Install dependencies:

   npm install or bun add
   

3. Start the development server (optional):

   npm run dev or bun run dev
   

4. Build the project:

   npm run build or bun run build
   

5. Run tests:

   npm test or bun test
   

💻 Usage Examples

Environment Variables

• PORT: Specify the port on which the server runs, defaulting to 3000.
• DEBUG: Enable debug mode by setting the value to true.

Resource URIs

The following are the resource URIs provided by the MCP server:

Example Requests

Create a New Collection

POST /api/collections
Content-Type: application/json

{
  "name": "My New Collection",
  "description": "My first MCP collection"
}

Search for Bookmarks

GET /api/items?search=technology
HTTP/1.1

🤝 Contribution

Contributions are welcome! Please open an issue or submit a pull request.

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.