AI Tools for Varity

Varity Team Core Contributors Updated March 2026

Varity provides AI tooling to help you build faster. Copy a prompt into your AI assistant, and it already knows how to build, deploy, and debug Varity apps.

Available Tools

AI Prompts

Ready-to-use prompts for Cursor, Claude Code, Copilot, and any AI assistant. Copy a prompt, start building.

View Prompts →

Cursor Rules

.mdc rule files that teach Cursor how to write Varity code. Drop into your project for intelligent autocomplete.

LLM-Optimized Docs

Machine-readable documentation for AI assistants. Available in two formats: /llms.txt (summary) and /llms-full.txt (detailed).

MCP Server

Model Context Protocol server for Cursor, Claude Code, VS Code, and Windsurf — deploy, search docs, and manage apps from your AI editor.

View Spec →

Quick Start: AI Prompts

The fastest way to get AI assistance with Varity is to copy one of our AI Prompts into your project.

For Cursor:

1. Copy the Varity rules from our AI Prompts page
2. Save to .cursor/rules/varity.mdc in your project
3. Cursor now understands Varity patterns automatically

For Claude Code:

1. Copy the prompt content from our AI Prompts page
2. Add to your project’s CLAUDE.md file
3. Claude Code now has full Varity context

For any AI assistant:

1. Copy the prompt from AI Prompts
2. Paste at the start of your conversation
3. Ask it to build features using Varity

Quick Start: MCP Server

The Varity MCP server lets your AI editor create, deploy, and manage Varity apps directly.

For Cursor — add to .cursor/mcp.json:

{
  "mcpServers": {
    "varity": {
      "command": "npx",
      "args": ["-y", "@varity-labs/mcp"]
    }
  }
}

For Claude Code:

claude mcp add varity -- npx -y @varity-labs/mcp

Then ask your AI to “create a Varity app” or “deploy this project” — it has 7 tools for the full build-to-monetize workflow. See the MCP Server Spec for the complete tool reference.

Cursor Rules

Pre-configured rules that teach Cursor IDE how to write Varity code correctly.

Available rules:

• Varity App Development — SDK patterns, database queries, auth setup
• Deployment — CLI commands, environment variables, hosting options
• Authentication — Auth setup, protected routes, user data
• Database — Collections, typed queries, CRUD hooks

Install:

mkdir -p .cursor/rules
# Copy rule content from the AI Prompts page into .cursor/rules/varity.mdc

See the AI Prompts page for the full rules file content.

LLM-Optimized Documentation

AI assistants can reference our documentation in machine-readable formats:

File	URL	Use Case
llms.txt	https://docs.varity.so/llms.txt	Summary — what Varity is, key APIs, common patterns
llms-full.txt	https://docs.varity.so/llms-full.txt	Detailed — full documentation content for deep context

Point any AI tool at one of these URLs for instant Varity context. Use llms.txt for quick context in chat-based LLMs (ChatGPT, Gemini), and llms-full.txt when the AI needs comprehensive documentation.

AI-Friendly Patterns

Our tools teach AI assistants these patterns:

Infrastructure Abstraction

AI assistants are trained to use developer-friendly language:

• “Deploy your application” (not “upload to IPFS”)
• “Sign in” (not “connect wallet”)
• “Usage fees are covered” (not “gasless transactions”)

Type Safety

import { db } from '@varity-labs/sdk';
import type { Project } from '../types';

// Always use typed collections
const projects = db.collection<Project>('projects');

Error Handling

try {
  await projects.add(data);
} catch (error) {
  if (error.code === 'VALIDATION_ERROR') {
    // Handle specific error
  }
}

Supported AI Tools

Tool	Integration	Level
Cursor	MCP Server + .mdc rules + prompts	Full
Claude Code	MCP Server + CLAUDE.md + prompts	Full
VS Code (Copilot)	MCP Server + llms.txt context	Full
Windsurf	MCP Server + Cursor-compatible rules	Full
ChatGPT	llms.txt context	Basic
Gemini	llms.txt context	Basic
GitHub Copilot	llms.txt context	Basic

What’s Next

• AI Prompts — Ready-to-use prompts for every AI tool
• MCP Server Spec — Setup guide and tool reference