Raindrop.io MCP server for AI agents

Raindrop.io MCP Server is a bridge that connects AI language models to the Raindrop.io bookmarking service. It implements the Model Context Protocol (MCP) standard, allowing AI agents to interact with your bookmarks, collections, tags, and highlights in a structured way.

Getting Started

Prerequisites

Before using the Raindrop.io MCP Server, you'll need:

Node.js (v18 or later recommended) or Bun
A Raindrop.io account
A Raindrop.io API Access Token

To get your API token, go to your Raindrop.io settings and create a new API token.

Installation Options

Quick Start with NPX

The easiest way to get started is using npx, which doesn't require installation:

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

# Run the server
npx @adeze/raindrop-mcp

Installing from Source

If you prefer to install from source:

# Clone the repository
git clone https://github.com/adeze/raindrop-mcp.git
cd raindrop-mcp

# Install dependencies
bun install

# Configure Environment Variables
cp .env.example .env

Edit the .env file and add your Raindrop.io API Access Token:

RAINDROP_ACCESS_TOKEN=YOUR_RAINDROP_ACCESS_TOKEN

Then build and run the server:

bun run build
bun start

Using the MCP Server

Available Resources

The server exposes these resource URIs that you can access:

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

Configuring for AI Assistants

To connect the Raindrop MCP server with an AI assistant or other MCP-compatible clients, add this configuration to your .mcp.json file:

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

This registers the Raindrop server under the name "raindrop" and makes all resources and tools available to your AI assistant.

Capabilities

The server supports a wide range of operations:

Create, read, update, and delete bookmarks and collections
Search bookmarks with advanced filtering
Manage tags (list, rename, merge, delete)
Access text highlights from bookmarks
Manage collections (reorder, expand/collapse, merge)
Upload files directly to Raindrop.io
Set reminders for bookmarks
Import and export bookmarks
Empty the trash
Stream real-time bookmark updates

Running in HTTP Mode

If you prefer to run the server in HTTP mode instead of the default stdio mode:

bun run start:http

This makes the server available over HTTP, which can be useful for certain integrations or testing.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

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

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

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

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

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

3. Restart Claude Desktop for the changes to take effect