Raindrop

MCP server for the Raindrop.io personal knowledge management system.

python

7

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "ddltn-raindrop-mcp-python": {
      "command": "uv",
      "args": [
        "run",
        "mcp",
        "install",
        "server.py"
      ],
      "env": {
        "RAINDROP_TOKEN": "YOUR_TOKEN"
      }
    }
  }
}

You can read and manage your Raindrop.io bookmarks through an MCP server built with the Python MCP SDK. This server lets you read collections and raindrops, create or update items, and organize tags, all via natural language commands issued from an MCP client. It’s designed to work with Claude Desktop and pairs well with other MCP servers to extend your knowledge management workflows.

How to use

You will run this MCP server locally and connect to it from an MCP client. Start by installing the server, then activate development mode to test changes. Once running, you can ask the client to list your Raindrop collections, filter by keywords, inspect a specific collection by ID, view nested collections, or modify raindrops and collections. Use the available tools to create new collections, update existing ones, delete collections (moving items to Trash), empty the Trash, fetch individual raindrops, update raindrops, and manage tags. The server exposes these capabilities as MCP actions that your client can invoke through natural language queries.

How to install

Prerequisites you need before installing this server are Python 3.12 or newer and the uv package manager. You should also have a Raindrop.io account and generate an API token to access your data.

Create an environment variable for your Raindrop API token.
Install the MCP server package manager support so you can run MCP commands.
Install and run the MCP server locally using the provided MCP commands below.

uv run mcp install server.py
uv run mcp dev server.py

# Optional: set up a .env file for your token
RAINDROP_TOKEN="your_token_here" Note: The token can also be set as an environment variable in your shell or within a .env file at the project root.

Notes and setup details

Configuration is driven by environment variables and the server supports reading token values from a .env file or the environment. Create a .env file at the root of your project and add the token in this format.

RAINDROP_TOKEN="your_token_here"

Available tools

create_collection

Creates a new collection in Raindrop.io with a given title and optional view, public visibility, and parent collection.

update_collection

Updates properties of an existing Raindrop collection, including title, view, visibility, parent, and expanded state.

delete_collection

Deletes a collection; contained raindrops are moved to Trash by default.

empty_trash

Permanently deletes all raindrops currently in the Trash.

get_raindrop

Fetches a single raindrop (bookmark) by its ID.

get_raindrops

Retrieves multiple raindrops from a collection with options for sorting, pagination, and nested collections.

get_tags

Retrieves tags from Raindrop.io, optionally scoped to a specific collection.

update_raindrop

Updates a raindrop's title, link, description, tags, collection, cover image, and other metadata.

update_many_raindrops

Updates multiple raindrops within a collection in a single operation, applying common changes like tags, cover image, and target collection.