What do I need to use this server?
A Raindrop.io account and an API access token from the Raindrop.io integrations settings. The token must be passed as the `RAINDROP_ACCESS_TOKEN` environment variable.
@adeze
Basic information
Raindrop MCP Server
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"raindrop-mcp": {
"command": "npx",
"args": [
"skills",
"add",
"adeze/raindrop-mcp",
"--global"
]
}
}
}Server diagnostic information and library health metrics
List all collections as a flat list
Hierarchical view of collections with full breadcrumb paths
Create, update, or delete collections
Advanced search with filters, tags, and pagination
Create, update, or delete bookmarks
Fetch a single bookmark by ID
List bookmarks for a collection with pagination
AI-powered organization advice (tags/collections) for a URL or bookmark
Suggest relevant tags from bookmark metadata using AI-assisted analysis
Bulk update, move, or remove bookmarks in a specific collection
Rename, merge, or delete tags
Create, update, or delete highlights
Scan library for broken links, duplicates, and untagged items
Permanently empty the trash (requires confirmation)
Remove empty collections (requires confirmation)
Find and remove duplicate bookmarks with safe confirmation flow
Connects Raindrop.io — the bookmark management service — to AI assistants via the Model Context Protocol (MCP). It lets you organize, search, and manage bookmarks using natural language commands. Ideal for users who want to control their Raindrop.io library through tools like Claude, Gemini, or other MCP-compatible clients.
Install using a one-liner for your AI tool (e.g., npx -y @adeze/raindrop-mcp for most clients, or the MCPB bundle for Claude Desktop) and set the RAINDROP_ACCESS_TOKEN environment variable with your Raindrop.io API token. Alternatively, add the server to your MCP client’s configuration file (mcp.json) with the same command and environment variable.
A Raindrop.io account and an API access token from the Raindrop.io integrations settings. The token must be passed as the `RAINDROP_ACCESS_TOKEN` environment variable.
Export `RAINDROP_ACCESS_TOKEN` as an environment variable in your shell or in your MCP client’s configuration (e.g., `env` field in `mcp.json`).
Yes. Download the `raindrop-mcp.mcpb` bundle from the GitHub Releases and add it to Claude Desktop, setting the same environment variable.
Yes. `empty_trash`, `cleanup_collections`, and `remove_duplicates` require explicit confirmation before executing.
OAuth support is planned for a future release. Currently you must provide a manual API access token.
🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。
This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,
Hindsight: Agent Memory That Learns

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.
不止于 CSS
Comments