Raindrop.io
MCP Server for accessing Raindrop.io bookmark manager.
What is Raindrop.io?
Raindrop.io is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server for accessing raindrop.io bookmark manager.
MCP Server for accessing Raindrop.io bookmark manager.
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- MCP Server for accessing Raindrop.io bookmark manager.
Use Cases
Maintainer
Works with
Installation
NPM
npx -y raindrop.ioManual Installation
npx -y raindrop.ioConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Raindrop.io
The Raindrop.io MCP server connects your AI assistant to your Raindrop.io bookmark manager, exposing 17 tools for searching, creating, updating, and deleting bookmarks and collections, managing tags, reading highlights, bulk-editing, and auditing your library for broken links and duplicates. It communicates with the official Raindrop.io REST API using your personal access token, giving Claude, Cursor, Gemini CLI, or any MCP client natural-language control over your entire bookmark library. This makes it easy to find saved research, reorganize collections, or add new bookmarks without leaving your AI workflow.
Prerequisites
- A Raindrop.io account (free or Pro) at raindrop.io
- A Raindrop.io API Access Token from https://app.raindrop.io/settings/integrations
- Node.js 18 or newer (for the npx runner)
- An MCP-capable client: Claude Desktop, Claude Code, Cursor, Gemini CLI, or GitHub Copilot
Get your Raindrop.io API access token
Log in to Raindrop.io, navigate to Settings > Integrations, create a new integration, and copy the access token. This is your RAINDROP_ACCESS_TOKEN.
Set the access token in your environment
Export the RAINDROP_ACCESS_TOKEN so npx can pass it to the server at runtime.
export RAINDROP_ACCESS_TOKEN=your_raindrop_access_token_hereAdd the server to Claude Code
Use the Claude Code CLI to register the Raindrop MCP server. This adds it to your project or global MCP configuration.
claude mcp add raindrop -- npx -y @adeze/raindrop-mcpOr run directly with npx
You can test the server by running it directly from the command line with your access token set.
RAINDROP_ACCESS_TOKEN=your_token npx @adeze/raindrop-mcpAdd the server to Claude Desktop manually
Edit your claude_desktop_config.json to include the Raindrop MCP server configuration with your access token.
Raindrop.io Examples
Client configuration (Claude Desktop)
Add the Raindrop.io MCP server to Claude Desktop with your personal access token.
{
"mcpServers": {
"raindrop": {
"command": "npx",
"args": ["-y", "@adeze/raindrop-mcp"],
"env": {
"RAINDROP_ACCESS_TOKEN": "your_raindrop_access_token_here"
}
}
}
}Prompts to try
These prompts exercise the search, organization, and audit tools exposed by the Raindrop MCP server.
- "Search my bookmarks for articles about Rust performance"
- "Show me all bookmarks tagged with 'machine-learning'"
- "Create a new collection called 'AI Research' and move my AI bookmarks there"
- "Audit my library for broken links and duplicates"
- "List all my collections as a tree view"
- "Add a bookmark to https://example.com with tags 'reference' and 'tools'"Troubleshooting Raindrop.io
Authentication errors — 401 Unauthorized responses
Verify your RAINDROP_ACCESS_TOKEN is correct. Generate a fresh token at https://app.raindrop.io/settings/integrations and make sure the environment variable is exported before starting the server.
npx fails to find the package or times out
Ensure you have Node.js 18+ installed ('node --version'). Try running 'npx -y @adeze/raindrop-mcp@latest' to force the latest version download and bypass any cache issues.
Destructive operations like empty_trash or cleanup_collections don't execute
These tools require explicit confirmation as a safety measure. When prompted by the AI, confirm you want to proceed. The tool description will specify what confirmation string to use.
Frequently Asked Questions about Raindrop.io
What is Raindrop.io?
Raindrop.io is a Model Context Protocol (MCP) server that mcp server for accessing raindrop.io bookmark manager. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Raindrop.io?
Install via npm with the command: npx -y raindrop.io. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
Which AI clients work with Raindrop.io?
Raindrop.io works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Raindrop.io free to use?
Yes, Raindrop.io is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
Raindrop.io Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to Raindrop.io? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.
MemPalace
★ 52.6kA local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically
Kratos
★ 25.7k🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.
Context Mode
★ 15.4kAn MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm
Memu
★ 13.7kMemory for 24/7 proactive agents like OpenClaw.
MemOS
★ 9.3kMemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u
Everos
★ 5.4kBuild, evaluate, and integrate long-term memory for self-evolving agents.
Browse More Knowledge & Memory MCP Servers
Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Raindrop.io in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Raindrop.io?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.