raindrop.io
An MCP server for Raindrop.io
claude mcp add --transport stdio sachin-philip-raindrop.io-mcp uv --directory <location to project clone> run raindrop.py \ --env RAINDROP_TOKEN="<your_raindrop_token>"
How to use
This MCP server exposes Raindrop.io bookmark management capabilities to your LLM apps. It lets you add bookmarks with optional metadata (tags, description, and collection), retrieve the most recent bookmarks, and search your bookmarks by tag or by keyword. The implementation runs a Python script (raindrop.py) using UV, with your Raindrop.io API token supplied via the RAINDROP_TOKEN environment variable. To get started, ensure you have Python 3.11 and UV installed, then launch the server through UV as configured in the MCP config. Once running, you can call the available commands from your LLM or automation tooling to interact with your Raindrop.io account programmatically.
How to install
Prerequisites:
- Python 3.11
- UV package manager
Install UV:
curl -LsSf https://astral.sh/uv/install.sh | sh
Activate UV and install dependencies for your project:
uv activate && uv install
Set up your MCP configuration (see the example in the README):
- Create or clone the MCP server project.
- Ensure raindrop.py (the server script) is present in the project directory.
- Update your MCP config to point to the local path via --directory and provide your Raindrop.io API token in RAINDROP_TOKEN.
Run the MCP server via UV as configured:
# Example (adjust <location to project clone>):
uv --directory <location to project clone> run raindrop.py
Optional Smithery installation (for Claude Desktop users):
npx -y @smithery/cli install @sachin-philip/raindrop-io-mcp --client claude
Additional notes
Tips and notes:
- RAINDROP_TOKEN must be set and valid for the session running raindrop.py; without it, API calls will be unauthenticated.
- The MCP server name in the config is Raindrop and should reflect your preference; you can rename the server entry as needed.
- If you modify the project directory, update the --directory path in the MCP config accordingly.
- raindrop.py should implement handlers for: add bookmark (with tags, description, collection), get latest bookmarks, search by tag, and search by keyword/text.
- If you encounter token or API rate issues, verify network access and Raindrop.io token scopes in the Developer Portal.
- Logs from the UV process can aid debugging; ensure the environment running raindrop.py has access to the RAINDROP_TOKEN and network access to Raindrop.io.
Related MCP Servers
nautex
MCP server for guiding Coding Agents via end-to-end requirements to implementation plan pipeline
mcp-yfinance
Real-time stock API with Python, MCP server example, yfinance stock analysis dashboard
pfsense
pfSense MCP Server enables security administrators to manage their pfSense firewalls using natural language through AI assistants like Claude Desktop. Simply ask "Show me blocked IPs" or "Run a PCI compliance check" instead of navigating complex interfaces. Supports REST/XML-RPC/SSH connections, and includes built-in complian
cloudwatch-logs
MCP server from serkanh/cloudwatch-logs-mcp
servicenow-api
ServiceNow MCP Server and API Wrapper
the -company
TheMCPCompany: Creating General-purpose Agents with Task-specific Tools