Spark
Sign In
MCP Connector

Integrate Raindrop.io Bookmarks with LLMs

Create and search Raindrop.io bookmarks - filter by tags and collections - directly from Claude.

Connect
Works with raindrop.io
hiromitsusasaki
Maintainer?
90
Spark score
out of 100
Updated Jun 2025
Fresher alternatives ↓
Version 1.0.0
Models
claude
Add to Favorites

Why it matters

Enable Large Language Models to interact with your Raindrop.io bookmarks. Create, search, and filter your saved links using natural language commands.

Outcomes

What it gets done

01

Create new bookmarks in Raindrop.io via LLM prompts.

02

Search existing bookmarks using keywords and tags.

03

Filter bookmarks by specific tags and collections.

04

Connect LLMs to your Raindrop.io account securely.

Install

Add it to your toolbox

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/vb-raindrop-io | bash

Capabilities

Tools your agent gets

create-bookmark

Creates a new bookmark with optional title, tags, and collection ID

search-bookmarks

Searches bookmarks with optional tag-based filtering

Overview

Raindrop.io MCP Server

Raindrop.io MCP Server lets Claude create and search Raindrop.io bookmarks, with tag and collection filtering, authenticated via a Raindrop API token. Use it for conversational bookmark creation and search in Raindrop.io. Requires a RAINDROP_TOKEN kept secure via environment variables.

What it does

Raindrop.io MCP Server lets an AI assistant interact with your Raindrop.io bookmark collection, creating new bookmarks and searching existing ones by query or tags.

When to use - and when NOT to

Use it when you want Claude to save a URL to your Raindrop.io collection with a title, tags, and target collection ID, or search your existing bookmarks by keyword and/or tag filter. Do not use it without a Raindrop.io API token - RAINDROP_TOKEN is required and must be kept secure via environment variables rather than hardcoded in config files.

Capabilities

  • create-bookmark: create a new bookmark with url (required), title (optional), tags (optional array), and collection (optional collection ID).
  • search-bookmarks: search bookmarks with query (required) and tags (optional array to filter by).

How to install

Install automatically for Claude Desktop via Smithery:

npx -y @smithery/cli install @hiromitsusasaki/raindrop-io-mcp-server --client claude

Or manually:

git clone https://github.com/hiromitsusasaki/raindrop-io-mcp-server
cd raindrop-io-mcp-server
npm install
# create .env with RAINDROP_TOKEN=your_access_token_here
npm run build

Configure Claude Desktop:

{
  "mcpServers": {
    "raindrop": {
      "command": "node",
      "args": ["PATH_TO_BUILD/index.js"],
      "env": { "RAINDROP_TOKEN": "your_access_token_here" }
    }
  }
}

Requires Node.js 16+ and a Raindrop.io account with an API token.

Who it's for

Raindrop.io users who want Claude to save and search bookmarks conversationally instead of switching to the Raindrop.io app.

Source README

Raindrop.io MCP Server

smithery badge

An integration that allows LLMs to interact with Raindrop.io bookmarks using the Model Context Protocol (MCP).

Raindrop.io Server MCP server

Features

  • Create bookmarks
  • Search bookmarks
  • Filter by tags

Requirements

  • Node.js 16 or higher
  • Raindrop.io account and API token

Setup

Installing via Smithery

To install Raindrop.io Integration for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @hiromitsusasaki/raindrop-io-mcp-server --client claude

Manual Installation

  1. Clone the repository:
git clone https://github.com/hiromitsusasaki/raindrop-io-mcp-server
cd raindrop-io-mcp-server
  1. Install dependencies:
npm install
  1. Set up environment variables:
  • Create a .env file and set your Raindrop.io API token
RAINDROP_TOKEN=your_access_token_here
  1. Build:
npm run build

Using with Claude for Desktop

  1. Open Claude for Desktop configuration file:
  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  1. Add the following configuration:
{
  "mcpServers": {
    "raindrop": {
      "command": "node",
      "args": ["PATH_TO_BUILD/index.js"],
      "env": {
        "RAINDROP_TOKEN": "your_access_token_here"
      }
    }
  }
}
  1. Restart Claude for Desktop

Available Tools

create-bookmark

Creates a new bookmark.

Parameters:

  • url: URL to bookmark (required)
  • title: Title for the bookmark (optional)
  • tags: Array of tags (optional)
  • collection: Collection ID (optional)

search-bookmarks

Searches through bookmarks.

Parameters:

  • query: Search query (required)
  • tags: Array of tags to filter by (optional)

Development

# Build for development
npm run build

# Start server
npm start

Security Notes

  • Always manage API tokens using environment variables
  • Set appropriate permissions for Claude for Desktop configuration files
  • Restrict unnecessary file access

Open Source

This is an open source MCP server that anyone can use and contribute to. The project is released under the MIT License.

Related Links

FAQ

Common questions

Discussion

Questions & comments · 0

Sign In Sign in to leave a comment.