Skip to content
Raindrop Developer Hub

Cursor Setup for LiquidMetal

Setup Cursor editor to correctly generate LiquidMetal code based on your prompt.

Cursor LLM Setup

The docs.liquidmetal.ai/liquidmetal.txt file is a compact, text version of LiquidMetal manifest documentation to help AI generate accurate LiquidMetal code based on your prompt.

Here’s how to use LiquidMetal’s liquidmetal.txt in Cursor:

Quick Use

In chat window type this and Cursor will use LiquidMetal’s liquidmetal.txt file to generate code:

@web https://docs.liquidmetal.ai/liquidmetal.txt

Permanent Setup

  1. Press ⌘ CMD + ⇧ Shift + P. Or if it’s Windows, press ⌃ Ctrl + ⇧ Shift + P.
  2. Type Add new custom docs
  3. Add this: 
    https://docs.liquidmetal.ai/liquidmetal.txt
  4. Now in chat window you can type @docs and choose LiquidMetal to provide LiquidMetal docs to Cursor.

Project-Level Permanent Setup

You can setup LiquidMetal’s liquidmetal.txt file to your repo so Cursor can use it by default. This approach ensures that anyone working on your project gets the LiquidMetal context automatically.

Run this command in your project root to save the liquidmetal.txt file to .cursor/rules/liquidmetal.mdc:

Terminal window
curl -L https://docs.liquidmetal.ai/liquidmetal.txt --create-dirs -o .cursor/rules/liquidmetal.mdc

MCP Server

MCP (Model Context Protocol) is an API to communicate with AI models. You can add MCP servers and Cursor will communicate with them to get more accurate results.

We recommend using our official LiquidMetal MCP server which provides comprehensive LiquidMetal platform knowledge.

  1. Go to Cursor settings ⌘ CMD + ⇧ Shift + J (or ⌃ Ctrl + ⇧ Shift + J on Windows)
  2. Click MCP from the left sidebar
  3. Click Add new global MCP server
  4. Add the following:
{
  "mcpServers": {
    "LiquidMetal": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@liquidmetal/mcp-server@latest"]
    }
  }
}
  1. Now in Agent Mode you can ask AI anything about LiquidMetal, and write use liquidmetal at the end of your prompt.

For example:

create a raindrop application that processes uploaded documents and stores results in a database. use liquidmetal

Getting Help

Do you have a question? Ask on our GitHub Discussions or Discord server.

Do you like LiquidMetal? Star us on GitHub!