Raindrop.io MCP server

Integrates with Raindrop.io to enable natural language management of bookmarking collections and tags for streamlined organization workflows.
Back to servers
Provider
ddaltn
Release date
Apr 07, 2025
Language
Python
Stats
2 stars

This MCP server for Raindrop.io allows you to interact with your Raindrop bookmarks directly from Claude Desktop using simple, human language. You can manage collections, view bookmarks, and organize your personal knowledge system through natural conversation.

Installation Requirements

  • Python 3.12 or higher
  • uv package manager
  • Claude Desktop
  • A Raindrop.io account with API token

Setup Process

Obtaining a Raindrop API Token

  1. Navigate to the Raindrop.io Developer Portal
  2. Create a new app
  3. Copy your generated API token

Configuring Your API Token

Create a .env file in the project's root directory containing:

RAINDROP_TOKEN="your_token_here"

Installing the Server

To install the server to Claude Desktop:

uv run mcp install server.py

To run the server in development mode:

uv run mcp dev server.py

Using with Claude Desktop

After installation, you can interact with your Raindrop bookmarks by asking Claude questions or giving commands like:

  • "Show me all my Raindrop collections"
  • "Do I have any collections related to programming?"
  • "Add this tag to all raindrops in this collection"
  • "Show me the details of my Raindrop collection with ID 12345"
  • "Create a new Raindrop collection called 'Claude Resources'"

Available Tools and Commands

Collection Management

Creating Collections

create_collection
  • Required: title (name of the collection)
  • Optional: view (list, grid, masonry, simple), public (boolean), parent_id (ID for nested collections)

Updating Collections

update_collection
  • Required: collection_id
  • Optional: title, view, public, parent_id, expanded

Deleting Collections

delete_collection
  • Required: collection_id

Managing Trash

empty_trash

Permanently deletes all items in the trash.

Bookmark (Raindrop) Management

Retrieving Bookmarks

get_raindrop
  • Required: raindrop_id
get_raindrops
  • Required: collection_id (use 0 for all, -1 for unsorted, -99 for trash)
  • Optional: search, sort, page, perpage, nested

Updating Bookmarks

update_raindrop
  • Required: raindrop_id
  • Optional: title, excerpt, link, important, tags, collection_id, cover, type, order, pleaseParse
update_many_raindrops
  • Required: collection_id
  • Optional: ids, important, tags, cover, target_collection_id, nested, search

Tag Management

get_tags
  • Optional: collection_id (retrieves all tags when omitted)

Integration Example

This MCP server can be paired with the Firecrawl MCP server to read and classify URLs in your bookmarks, creating a powerful system for managing and understanding your saved content.

How to add this MCP server to 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 > MCP and click "Add new global MCP server".

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

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

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 explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later