raindrop-io
An integration that allows LLMs to interact with Raindrop.io bookmarks using the Model Context Protocol (MCP).
claude mcp add --transport stdio hiromitsusasaki-raindrop-io-mcp-server node PATH_TO_BUILD/index.js \ --env RAINDROP_TOKEN="yourRaindropIoApiToken"
How to use
This MCP server enables LLMs to interact with Raindrop.io bookmarks through the Model Context Protocol. It supports creating new bookmarks, searching bookmarks, and filtering results by tags. After starting the server, you can connect to it via MCP clients (such as Claude Desktop) and invoke the available tools to manage your Raindrop.io collection programmatically. The server expects an API token to authenticate with Raindrop.io, which you pass via the RAINDROP_TOKEN environment variable.
Available tools include:
- create-bookmark: Creates a new bookmark with fields like url, title, tags, and collection. This is useful for saving references surfaced by the LLM during a chat.
- search-bookmarks: Queries your Raindrops using a text query and optional tag filters. This helps fetch relevant bookmarks to reference in conversations or to retrieve context.
To use these tools, provide the required parameters (e.g., url for create-bookmark, query for search-bookmarks) and optional fields like title, tags, or collection. Ensure the RAINDROP_TOKEN is set in the runtime environment when the MCP server starts so the server can authenticate with Raindrop.io on behalf of your account.
How to install
Prerequisites:\n- Node.js 16 or higher\n- Git\n- Internet access to install dependencies\n\nStep-by-step installation:\n1. Clone the repository:\nbash\ngit clone https://github.com/hiromitsusasaki/raindrop-io-mcp-server.git\ncd raindrop-io-mcp-server\n\n2. Install dependencies:\nbash\nnpm install\n\n3. Set up environment variables:\n- Create a .env file in the project root and set your Raindrop.io API token:\nbash\nRAINDROP_TOKEN=your_access_token_here\n\n4. Build the project:\nbash\nnpm run build\n\n5. Start the server:\nbash\nnpm start\n\n\nNotes:\n- The README mentions a Smithery install option, but this guide covers manual setup.\n- Ensure your Node.js version matches the requirements (Node.js 16+).
Additional notes
Environment variables and configuration tips:\n- RAINDROP_TOKEN is required for authentication with Raindrop.io. Do not expose it in public configurations.\n- When using Claude Desktop, ensure the path in PATH_TO_BUILD/index.js points to the built server entry (from npm run build).\n- If you encounter authentication errors, double-check that RAINDROP_TOKEN is valid and has permissions to read and create bookmarks in Raindrop.io.\n- Build artifacts are typically placed in a build/output path; adjust PATH_TO_BUILD to reflect the actual output location after npm run build.\n- For production deployments, consider proper process management (e.g., using pm2 or systemd) and secure environment handling.
Related MCP Servers
inspector
Test & Debug MCP servers, ChatGPT apps, and MCP Apps (ext-apps)
MCP-Nest
A NestJS module to effortlessly create Model Context Protocol (MCP) servers for exposing AI tools, resources, and prompts.
OmniFocus
Let LLMs interface with your tasks and projects through the Model Context Protocol. Add, organize, and query your OmniFocus database with natural language commands.
zig
Model Context Protocol (MCP) server that provides up-to-date documentation for the Zig programming language standard library and builtin functions
elysia
ElysiaJS plugin for Model Context Protocol with HTTP transport
mcp-task-manager
A local Model Context Protocol (MCP) server providing backend tools for client-driven project and task management using a SQLite database.