Raindrop.io MCP Server

Created By

adeze8 months ago

Raindrop MCP Server

Content

Raindrop.io MCP Server

This project provides a Model Context Protocol (MCP) server for interacting with the Raindrop.io bookmarking service. It allows Language Models (LLMs) and other AI agents to access and manage your Raindrop.io data through the MCP standard.

Features

CRUD Operations: Create, Read, Update, and Delete collections and bookmarks.
Advanced Search: Filter bookmarks by various criteria like tags, domain, type, creation date, etc.
Tag Management: List, rename, merge, and delete tags.
Highlight Access: Retrieve text highlights from bookmarks.
Collection Management: Reorder, expand/collapse, merge, and remove empty collections.
File Upload: Upload files directly to Raindrop.io.
Reminders: Set reminders for specific bookmarks.
Import/Export: Initiate and check the status of bookmark imports and exports.
Trash Management: Empty the trash.
MCP Compliance: Exposes Raindrop.io functionalities as MCP resources and tools.
Streaming Support: Provides real-time SSE (Server-Sent Events) endpoints for streaming bookmark updates.
Built with TypeScript: Strong typing for better maintainability.
Uses Axios: For making requests to the Raindrop.io API.
Uses Zod: For robust schema validation of API parameters and responses.
Uses MCP SDK: Leverages the official @modelcontextprotocol/sdk.

Prerequisites

Node.js (v18 or later recommended) or Bun
A Raindrop.io account
A Raindrop.io API Access Token (create one in your Raindrop.io settings)

Installation and Usage

Using NPX (Recommended)

You can run the server directly using npx without installing it:

# Set your API token as an environment variable
export RAINDROP_ACCESS_TOKEN=YOUR_RAINDROP_ACCESS_TOKEN

# Run the server
npx @adeze/raindrop-mcp

From Source

Clone the repository:

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

Install dependencies:
```
bun install
```
Configure Environment Variables: Create a .env file in the root directory by copying the example:
```
cp .env.example .env
```
Edit the .env file and add your Raindrop.io API Access Token:
```
RAINDROP_ACCESS_TOKEN=YOUR_RAINDROP_ACCESS_TOKEN
```
Build and Run:
```
bun run build
bun start
```

The server uses standard input/output (stdio) for communication by default, listening for requests on stdin and sending responses to stdout.

Usage with MCP Clients

Connect your MCP client (like an LLM agent) to the running server process via stdio. The server exposes the following resource URIs:

collections://all - All collections
collections://{parentId}/children - Child collections
tags://all - All tags
tags://collection/{collectionId} - Tags filtered by collection
highlights://all - All highlights
highlights://raindrop/{raindropId} - Highlights for a specific bookmark
highlights://collection/{collectionId} - Highlights filtered by collection
bookmarks://collection/{collectionId} - Bookmarks in a collection
bookmarks://raindrop/{id} - Specific bookmark by ID
user://info - User information
user://stats - User statistics

It also provides numerous tools for operational tasks such as collection management, bookmark operations, tag management, highlight operations, and user operations. For a detailed list of all available tools, refer to CLAUDE.md or check src/services/mcp.service.ts for definitions of resources and tools.

MCP Configuration

To use the Raindrop MCP server with your AI assistant or MCP-compatible client, you can add the following configuration to your .mcp.json file:

"raindrop": {
  "command": "npx",
  "args": [
    "@adeze/raindrop-mcp"
  ],
  "env": {
    "RAINDROP_ACCESS_TOKEN": "YOUR_RAINDROP_API_TOKEN"
  }
}

For Claude Code or other MCP-compatible clients, this will register the Raindrop server under the name "raindrop" and make all of its resources and tools available to your AI assistant.