The Raindrop.io MCP server allows you to interact with your Raindrop.io bookmarks through the Model Context Protocol (MCP). It enables searching, creating bookmarks, and retrieving collections from your Raindrop.io account.
Before using the raindrop-mcp server, you need to obtain an access token from Raindrop.io:
You can run the raindrop-mcp server in three different modes:
Create a JSON configuration file for the MCP server:
{
"mcpServers": {
"raindrop": {
"command": "npx",
"args": ["-y", "raindrop-mcp"],
"env": {
"RAINDROP_ACCESS_TOKEN": "<your-token>"
}
}
}
}
Replace <your-token>
with the access token you obtained from Raindrop.io.
Run the server with the SSE (Server-Sent Events) option:
npx -y raindrop-mcp --sse
Run the server with the HTTP streaming option:
npx -y raindrop-mcp --http
The raindrop-mcp server provides three main capabilities:
Each of these operations will be available through the MCP interface once you've set up the server with your access token.
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json
file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json
file.
To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"cursor-rules-mcp": {
"command": "npx",
"args": [
"-y",
"cursor-rules-mcp"
]
}
}
}
To add an MCP server to a project you can create a new .cursor/mcp.json
file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.