Build an App Using Only AI (No Code Required)

Varity Team Core Contributors Updated April 2026

This tutorial shows you how to build and deploy a production-ready SaaS app using only natural language prompts. No coding knowledge required—you’ll use Varity’s MCP server in Cursor or Claude Code to handle everything from scaffolding to deployment to monetization.

Tip

The entire workflow takes 10-15 minutes and costs ~70% less than AWS or Vercel.

What You’ll Build

A client invoicing dashboard with:

• User authentication (email + social login)
• Database for storing invoices
• CRUD operations (create, read, update, delete)
• Production hosting
• App Store listing for monetization

All without writing a single line of code.

Prerequisites

Install the following (one-time setup):

1. Cursor or Claude Code (AI editor with MCP support)

2. Node.js 18+ — download here

3. Python 3.8+ — download here

4. Varity MCP — install with:

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

   Or for Cursor, add to .cursor/mcp.json:

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

That’s it. No blockchain wallets, no crypto, no cloud accounts.

Step-by-Step

1. Check your setup

   In Cursor or Claude Code, type:

   “Check if my Varity environment is set up correctly”

   What happens: The AI runs varity_doctor to verify Node.js, npm, and varitykit are installed.

   Expected output:

   ✓ Node.js version: 20.0.0
   ✓ npm version: 10.0.0
   ✓ varitykit CLI: installed
   ✓ All checks passed!

   If any checks fail, the AI will guide you through fixing them.

2. Create your app

   Prompt:

   “Create a new Varity app called invoice-manager”

   What happens: The AI runs varity_init to scaffold a complete Next.js SaaS template with authentication, database, and UI components.

   Expected output:

   ✓ Created project at ./invoice-manager
   ✓ Template: SaaS Starter
   ✓ Included: Auth, database, dashboard, landing page

   You now have a fully working app—without writing any code.

3. Add your data model

   Prompt:

   “Add a collection called invoices with fields: customerName (string), amount (number), dueDate (Date), status (string with options: draft, sent, paid, overdue)”

   What happens: The AI runs varity_add_collection to create:

   • TypeScript type definition for Invoice
   • Database collection accessor
   • React hook (useInvoices()) with CRUD operations
   • (Optional) Dashboard page with table and form

   Expected output:

   ✓ Created Invoice type in src/types/index.ts
   ✓ Added invoices() collection to src/lib/database.ts
   ✓ Generated useInvoices() hook in src/lib/hooks.ts

4. Install dependencies

   Prompt:

   “Install the dependencies for my project”

   What happens: The AI runs varity_install_deps to install all npm packages.

   Expected output:

   ✓ Installing dependencies...
   ✓ Installed 247 packages

5. Preview locally

   Prompt:

   “Start the dev server and open it in my browser”

   What happens:

   • AI runs varity_dev_server with action: "start"
   • AI runs varity_open_browser with the localhost URL

   Expected output:

   ✓ Dev server running at http://localhost:3000
   ✓ Opening in default browser...

   Your app opens in the browser. You can:

   • Sign in with email (or Google/GitHub)
   • See the dashboard
   • Create, edit, and delete invoices

   Note

   All data is stored locally during development. When you deploy, it switches to production database automatically.

6. Build for production

   Prompt:

   “Build my app for production”

   What happens: The AI runs varity_build to compile and optimize the app.

   Expected output:

   ✓ Detected framework: Next.js
   ✓ Running build...
   ✓ Build completed successfully
   ✓ Output: 2.4 MB (optimized)

7. Deploy to production

   Prompt:

   “Deploy my app to production”

   What happens: The AI runs varity_deploy to:

   • Upload your app to distributed hosting
   • Inject production credentials (auth, database)
   • Generate a live URL

   Expected output:

   ✓ Deploying invoice-manager...
   ✓ Build: 100%
   ✓ Upload: 100%
   ✓ Live at: https://invoice-manager-abc123.varity.app

   Your app is now live on the internet. Anyone can access it.

8. Check deployment status

   Prompt:

   “Show me my deployment status”

   What happens: The AI runs varity_deploy_status to show all deployments.

   Expected output:

   Deployment: abc123
     URL: https://invoice-manager-abc123.varity.app
     Status: active
     Framework: Next.js
     Size: 2.4 MB
     Created: 2 minutes ago

9. Monetize your app

   Prompt:

   “Submit my app to the Varity App Store for $29 per month”

   What happens: The AI runs varity_submit_to_store to:

   • List your app on store.varity.so
   • Set up automatic billing (90% to you, 10% to Varity)
   • Make it discoverable to users

   Expected output:

   ✓ Submitted to App Store
   ✓ Listing: Invoice Manager
   ✓ Price: $29/month
   ✓ Your revenue: $26.10 per user per month (90%)
   ✓ Live at: https://store.varity.so/apps/invoice-manager

   Users can now find, subscribe to, and use your app. You earn revenue automatically.

10. Compare costs

    Prompt:

    “How much would this cost to host for 500 users on Varity vs AWS?”

    What happens: The AI runs varity_cost_calculator to show cost breakdown.

    Expected output:

    Hosting costs for 500 users:
    
    AWS:
      - Hosting: $120/month
      - Database: $80/month
      - Auth: $50/month
      - Total: $250/month
    
    Varity:
      - All-in-one: $75/month
      - Savings: $175/month (70% cheaper)
    
    Revenue (500 users × $29/mo):
      - Gross: $14,500/month
      - Your share (90%): $13,050/month
      - Varity fee (10%): $1,450/month
      - Net profit: $12,975/month

What Just Happened?

Let’s recap what you accomplished—without writing code:

1. ✅ Created a production SaaS app — Authentication, database, dashboard
2. ✅ Added a custom data model — Invoice collection with TypeScript types
3. ✅ Deployed to production — Live URL on distributed infrastructure
4. ✅ Listed on the App Store — Users can subscribe and pay
5. ✅ Set up revenue stream — 90% of subscription revenue goes to you

Total time: 10-15 minutes
Total cost: 70% less than AWS/Vercel
Code written: 0 lines

Next Steps

Now that you have a live, monetized app, you can:

• Add more features: “Add a clients collection with name, email, and company fields”
• Customize the UI: “Change the primary color to purple” (edit src/app/globals.css)
• View analytics: “Show me deployment logs” → varity_deploy_logs
• Scale up: “How much would 5,000 users cost?” → varity_cost_calculator

Advanced Prompts

Add authentication customization:

“Allow users to sign in with Apple and Twitter in addition to email and Google”

Add a new page:

“Create a reports page that shows total invoices, paid vs unpaid, and revenue this month”

Add relationships:

“Create a clients collection and link each invoice to a client”

Deploy updates:

“Deploy my latest changes to production”

Check revenue:

“How many users have subscribed to my app?” (coming soon—App Store analytics)

Behind the Scenes

When you prompt the AI, here’s what Varity does:

Your Prompt	MCP Tool	What Happens
”Create a new app”	varity_init	Scaffolds Next.js SaaS template locally
”Add a collection”	varity_add_collection	Generates TypeScript types, DB accessors, hooks
”Start dev server”	varity_dev_server	Runs npm run dev, returns localhost URL
”Build for production”	varity_build	Compiles app, optimizes bundle
”Deploy”	varity_deploy	Uploads to CDN, injects prod credentials
”Submit to store”	varity_submit_to_store	Lists app, sets up billing
”Show status”	varity_deploy_status	Fetches deployment info
”Compare costs”	varity_cost_calculator	Calculates Varity vs AWS/Vercel

Every tool runs locally or via Varity’s infrastructure—no manual configuration needed.

Troubleshooting

“varitykit not found”

Install the CLI:

pip install varitykit
varitykit doctor

“Cannot find module @varity-labs/mcp”

Verify Node.js 18+ is installed:

node --version

MCP server not showing in Cursor

Restart Cursor after adding .cursor/mcp.json. Verify the JSON is valid.

Deploy fails

Ask the AI:

“Show me the build logs for my last deployment”

The AI runs varity_deploy_logs to debug.

Why This Works

Traditional app development requires:

• Learning 5+ technologies (Next.js, React, Tailwind, Postgres, Auth0)
• Configuring cloud infrastructure (AWS, Vercel, Supabase)
• Writing 1,000+ lines of boilerplate code
• Managing environment variables, credentials, deployments

Varity eliminates all of that:

• Pre-built templates with best practices baked in
• Auto-configuration of auth, database, hosting
• AI-powered workflow via MCP tools
• One-command deploys with automatic credential injection

Result: You can build production apps in minutes instead of weeks.

Cost Breakdown

For a typical SaaS app with 500 users:

Traditional Stack (AWS + Vercel + Auth0):

• Hosting: $120/month
• Database: $80/month
• Auth: $50/month
• Total: $250/month

Varity Stack:

• All-in-one: $75/month
• Total: $75/month
• Savings: $175/month (70%)

Plus, Varity handles all configuration—no DevOps engineer needed.

Support

If you get stuck:

• Discord: discord.gg/7vWsdwa2Bg — ask in #general
• Docs: docs.varity.so
• MCP Reference: MCP Server Spec

Related Tutorials

• Build a SaaS App (Traditional) — Step-by-step with CLI commands
• Customize the Template — Change colors, branding, data models
• Add a CRUD Feature — Add new collections and pages