Beginner7 min read
Was this chapter helpful?
Share
Three very different doors into the same building. Here's how to pick the right one without overthinking it.
A service like Supabase doesn't give you just one way to connect — it usually gives you three. Each one is for a different moment in your build.
For your AI tool
Lets Claude Code or Cursor plug directly into a service while it builds. Your AI reads your database, looks up Stripe customers, checks deploys — without you copy-pasting.
For your app
The door your deployed app uses to talk to a service for real users. Fetches data, processes payments, sends emails — while people are using your site.
For your computer
Commands you (or your AI) type in the terminal to set things up, run migrations, or deploy. One-time jobs — not things your live app does.
MCP stands for Model Context Protocol. It's a standard, built by Anthropic, that lets AI tools like Claude Code and Cursor connect directly to outside services. Once you set up an MCP, your AI can do thingsin that service on its own — no tab switching, no copy-pasting, no "here's my API key, go look this up."
Think of it as
Giving your AI assistant a set of keys. With the Supabase MCP, Claude can open your database and read rows directly. With the GitHub MCP, it can check your open pull requests. With the Stripe MCP, it can look up a customer's subscription.
Rule of thumb
If you keep copy-pasting something from a dashboard into your AI chat, there's probably an MCP for that. Set it up once.
An API is the door your deployed appwalks through to talk to someone else's service. This is the classic setup: your site running on the internet needs weather data, so it calls a weather API. A user clicks "Pay" and your site calls the Stripe API. A user signs up and your site calls the Supabase API to save them to the database.
Think of it as
A phone line between your app and another company's computer. It stays open as long as your app is running. Every user action might trigger a new call.
Rule of thumb
If a real user has to trigger the action, it's an API. APIs run while your app is live, at the speed of your users' clicks.
A CLI (command line interface) is a little program you install on your computer that lets you type one-line commands to a service. You use it for one-time setup jobs — the stuff you do before or around building, not the stuff your live app does.
Think of it as
A toolbox on your workbench. You reach for it when you need to build a shelf, not every time someone walks past. Your AI tool (Claude Code, Cursor) can run CLI commands for you — you rarely need to type them yourself.
vercel deploy — push your site livesupabase migration new — create a new database changestripe listen — test webhooks on your laptopgh pr create — open a pull request on GitHubRule of thumb
If it's a setup step, deploy step, or database migration — it's the CLI. Your AI runs these for you.
Most modern platforms offer all three. Here's how Supabase does it — the pattern repeats everywhere.
Postgres database + auth + storage
Supabase MCP
Let Claude Code read your tables, check your row-level security policies, and debug queries live. No screenshotting the dashboard.
Supabase API (client library)
Your deployed app uses supabase.from("posts").select() to fetch blog posts for visitors in real time.
Supabase CLI
Run supabase login once, then supabase db push to ship a schema change.
Once you see it, you can't un-see it. Three popular services, same three-door setup.
| Service | MCP | API | CLI |
|---|---|---|---|
| Stripe | Let AI look up customers & debug failed payments | Your checkout page charges real cards | stripe listen to test webhooks locally |
| Vercel | Let AI read deploy logs & env vars | Programmatic deploys from another service | vercel deploy from your terminal |
| GitHub | Let AI read issues, PRs & comments | Your app shows repo activity to users | gh pr create to open pull requests |
When you don't know which door to walk through, ask these in order.
1. Is my AI doing this right now while helping me build?
Yes → MCP. (Reading your DB to help debug, looking up a Stripe customer, etc.)
2. Will this need to happen when real users click around my site?
Yes → API. (Fetching data, saving forms, processing payments.)
3. Is this a one-time setup, deploy, or migration step?
Yes → CLI. (Creating the project, pushing a schema change, shipping to production.)
You're building a SaaS and want to add Stripe. You'll actually touch all three: the CLI gets Stripe set up on your machine and tests webhooks. The API runs your live checkout when users pay. The MCP lets Claude read your Stripe dashboard while debugging failed subscriptions.
Build this with AI
"I want to add Stripe subscriptions to my Next.js app. Please do three things: (1) Install the Stripe CLI and walk me through logging in so we can test webhooks locally. (2) Build a /api/checkout route that uses the Stripe API to create a checkout session and redirect the user. (3) If an MCP for Stripe is available in my setup, use it to verify my products and prices are configured correctly in my Stripe account before writing the checkout code."
Paste these into Claude Code, Cursor, or whichever AI tool you use.
Set up the Supabase MCP in my project so you can read my database directly while helping me code. Walk me through getting the access token from my Supabase dashboard, adding the MCP config, and restarting the editor. Then confirm you can see my tables.
Add a /api/checkout route to my Next.js app that calls the Stripe API to create a checkout session for a $19/month subscription. Use an environment variable for the Stripe secret key. Show me a Subscribe button on the pricing page that redirects to Stripe.
Install the Vercel CLI on my computer, log me in, and deploy my current project. Walk me through each command, explain what it's doing, and tell me the live URL when it's done.
I want to [describe what you're trying to do]. Tell me whether I need an MCP, an API, or a CLI for this — and why. If I need more than one, explain the order I should set them up in.
Two quick prompts to use right away.
AUDIT WHAT I'M USING
"Look at my project and tell me which MCPs, APIs, and CLIs I'm currently using. For each one, explain what it's doing and whether I'm using the right tool for the job — or whether I should switch to a different one."
SUGGEST MCPS FOR MY STACK
"Based on the services in my project, suggest which MCPs I should install for my AI coding tool. Explain what each MCP would let you do that you can't do today, and walk me through installing the top 2 in priority order."