Raindrop.io MCP Server Integration

What does “Raindrop.io” MCP Server do?

The Raindrop.io MCP Server is an integration that enables Large Language Models (LLMs) and AI assistants to interact programmatically with Raindrop.io bookmarks via the Model Context Protocol (MCP). By serving as a bridge between AI clients and Raindrop.io’s bookmarking platform, this server allows users to create new bookmarks, search through existing ones, and filter results using tags. It greatly enhances AI-driven workflows by allowing agents to manage and access a user’s bookmark collection, making it possible to automate knowledge organization, retrieve relevant resources, and streamline content curation from within development tools or conversational AI interfaces. This empowers developers and AI users to build, share, and act on web resources directly through their preferred MCP-compatible environments.

List of Prompts

No prompt templates are mentioned in the repository.

List of Resources

No explicit resources are described in the repository.

List of Tools

• Create bookmarks: Allows the AI to add new bookmarks to the user’s Raindrop.io collection.
• Search bookmarks: Enables querying bookmarks based on various criteria.
• Filter by tags: Provides the ability to retrieve bookmarks filtered by specific tags.

Use Cases of this MCP Server

• Bookmark Management: Automate the addition and organization of bookmarks directly from AI agents.
• Knowledge Retrieval: Quickly search and access saved bookmarks relevant to a topic or task within development or chat environments.
• Content Curation: Filter and present web resources by tags for research, learning, or sharing with teams.
• Personal Knowledge Base: Build intelligent workflows that treat bookmarks as a dynamically accessible knowledge base.
• AI-Driven Workflow Automation: Integrate with other tools and platforms to trigger actions (like saving a link or searching bookmarks) as part of larger, automated flows.

How to set it up

Windsurf

No specific instructions are provided for Windsurf. General MCP server configuration applies if supported.

Claude

1. Ensure Node.js 16+ is installed and obtain a Raindrop.io API token.
2. Install via Smithery:

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

3. Set the environment variable:
   • Create a .env file with:

     RAINDROP_TOKEN=your_access_token_here
     

4. Open the Claude Desktop config (claude_desktop_config.json on macOS or Windows).
5. Add the MCP server config as follows:

   {
     "mcpServers": {
       "raindrop-io": {
         "command": "npx",
         "args": [
           "-y",
           "@smithery/cli",
           "start",
           "@hiromitsusasaki/raindrop-io-mcp-server",
           "--client",
           "claude"
         ],
         "env": {
           "RAINDROP_TOKEN": "your_access_token_here"
         }
       }
     }
   }
   

6. Save and restart Claude Desktop to apply changes.

Cursor

No instructions or config examples are provided for Cursor.

Cline

No instructions or config examples are provided for Cline.

Securing API Keys

Environment variables should be used to secure API keys. Example:

"env": {
  "RAINDROP_TOKEN": "your_access_token_here"
}

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "raindrop-io": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “raindrop-io” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Our opinion

This MCP server provides essential bookmark management features and easy setup for Claude Desktop, but lacks documented prompt templates and explicit resource definitions. No information was found about support for Roots or Sampling. Its documentation is clear, and it is functional for bookmark workflows, but broader integration examples and advanced MCP features are missing.

Rating: 6/10

MCP Score