Raindrop.io MCP server for AI agents

The Raindrop MCP Server is a tool that allows you to interact with your Raindrop.io bookmarks using natural language through Claude Desktop. It enables you to view, create, update, and manage your collections and bookmarks by simply asking questions or giving commands in plain English.

Requirements

Python 3.12+
uv package manager
Claude Desktop
A Raindrop.io account and API token

Installation

Get a Raindrop API Token

Go to the Raindrop.io Developer Portal
Create a new app
Copy your API token

Set Up Your Environment

Create a .env file in the root directory
Add your API token:
```
RAINDROP_TOKEN="your_token_here"
```

Install the Server

To install the server to Claude Desktop:

uv run mcp install server.py

Usage

Starting the Server

For testing or development, you can run the server in development mode:

uv run mcp dev server.py

Example Queries

Once installed in Claude Desktop, you can ask questions and give 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"
"What child collections do I have in Raindrop?"
"Create a new Raindrop collection called 'Claude Resources'"

Available Tools

Collection Management

create_collection

Creates a new collection in Raindrop.io.

Parameters:

title (required): Name of the collection
view: View type (list, grid, masonry, simple)
public: Whether the collection is public
parent_id: ID of parent collection (omit for root collection)

update_collection

Updates an existing collection in Raindrop.io.

Parameters:

collection_id (required): ID of the collection to update
title: New name for the collection
view: View type (list, grid, masonry, simple)
public: Whether the collection is public
parent_id: ID of parent collection (omit for root collection)
expanded: Whether the collection is expanded

delete_collection

Deletes a collection from Raindrop.io. The raindrops will be moved to Trash.

Parameters:

collection_id (required): ID of the collection to delete

Raindrop Management

get_raindrop

Gets a single raindrop from Raindrop.io by ID.

Parameters:

raindrop_id (required): ID of the raindrop to fetch

get_raindrops

Gets multiple raindrops from a Raindrop.io collection.

Parameters:

collection_id (required): ID of the collection to fetch raindrops from. Use 0 for all raindrops, -1 for unsorted, -99 for trash.
search: Optional search query
sort: Sorting order (options: -created, created, score, -sort, title, -title, domain, -domain)
page: Page number (starting from 0)
perpage: Items per page (max 50)
nested: Whether to include raindrops from nested collections

update_raindrop

Updates an existing raindrop (bookmark) in Raindrop.io.

Parameters:

raindrop_id (required): ID of the raindrop to update
title: New title for the raindrop
excerpt: New description/excerpt
link: New URL
important: Set to True to mark as favorite
tags: List of tags to assign
collection_id: ID of collection to move the raindrop to
cover: URL for the cover image
type: Type of the raindrop
order: Sort order (ascending) - set to 0 to move to first place
pleaseParse: Set to True to reparse metadata (cover, type) in the background

update_many_raindrops

Updates multiple raindrops at once within a collection.

Parameters:

collection_id (required): ID of the collection containing raindrops to update
ids: Optional list of specific raindrop IDs to update
important: Set to True to mark as favorite, False to unmark
tags: List of tags to add (or empty list to remove all tags)
cover: URL for cover image (use '' to set screenshots for all)
target_collection_id: ID of collection to move raindrops to
nested: Include raindrops from nested collections
search: Optional search query to filter which raindrops to update

Other Utilities

empty_trash

Empties the trash in Raindrop.io, permanently deleting all raindrops in it.

get_tags

Gets tags from Raindrop.io.

Parameters:

collection_id: Optional ID of the collection to fetch tags from. When not specified, all tags from all collections will be retrieved.

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-mcp-python" '{"command":"uv","args":["run","mcp","dev","server.py"]}'

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-mcp-python": {
            "command": "uv",
            "args": [
                "run",
                "mcp",
                "dev",
                "server.py"
            ]
        }
    }
}

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-mcp-python": {
            "command": "uv",
            "args": [
                "run",
                "mcp",
                "dev",
                "server.py"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect