Add a Redis-compatible cache to your app with your AI (2026)
Is your app slowing down under load? Ask your AI for a cache: connected to while over MCP, it declares one in three lines, and your app finds it in REDIS_URL.
By Aloïs Oddon, co-founder of Nextmap. Facts checked on November 19, 2026.
The short version. Over MCP, your AI adds a Redis-compatible cache to your app, with no server to manage. Its address arrives in REDIS_URL, password included. What matters, like deleting a database, waits for a person’s approval.
Prerequisites
- A Node.js, Python or Go app.
- An AI that works in a terminal: Claude Code, Codex, Cursor or Gemini CLI.
Step 1: Give your AI this message
Open your AI in your app’s folder, and paste this message into it:
Connect to while with my account (while.sh/agents), then put my app on while.
Your AI adds while’s MCP server itself. If it asks you to, restart it. On the first call to while, a page opens in your browser. In Claude Code, if it doesn’t open, type /mcp, choose while, then Authenticate. On that page, choose “A new app”, then click Authorize.
Step 2: Open your app
Your AI gives you your app’s address, for example https://mon-appli.while.cloud, over HTTPS.
What your AI does
It adds three lines to while.yaml:
apiVersion: while/v1
project: mon-appli
services:
- name: web
port: 3000
health:
path: /health
caches:
- name: cache
memory: 256Mi
The last three lines declare a 256 MiB Redis-compatible cache. Its address, password included, reaches your app in REDIS_URL1:
import { createClient } from 'redis';
const cache = createClient({ url: process.env.REDIS_URL });
await cache.connect();

Make the cache bigger
You, to your AI: Increase the cache to 512 MiB.
Your AI changes memory in while.yaml. When the cache is full, the keys that have gone unused the longest make room for new ones.
Keep the data after a restart
You, to your AI: Turn the cache into a job queue that never loses anything.
Your AI makes the cache durable: its data is written to disk, and no key is evicted.
Add a database
You, to your AI: Add a PostgreSQL database.
Your AI declares the database in while.yaml, and its address reaches your code in DATABASE_URL. The database is backed up every day, with a way back to a precise moment over 14 days.
Restrict your app to your colleagues
You, to your AI: Restrict the app to people in the company.
Your AI makes the service internal:
access: internal
Then it asks for the Access role for your domain, @acme.com, on this app, and a person in your organization approves it.
Once your Google Workspace or Microsoft 365 is linked to while, on the Pro plan, your colleagues sign in with their usual account, and your code receives their name and email address, with no sign-in page to write.
Go back to the previous version
You, to your AI: Go back to the previous version.
In the 30 minutes after a production release, the previous version comes back in a second. After that, it takes a few seconds. Once the previous version is back, your AI reads what broke in while’s logs, fixes it and deploys again.
In the docs: Valkey cache (Redis), PostgreSQL databases, Scheduled jobs, Internal access and Versions and rollback.
Next steps
Sources
- Redis, connecting a Node.js app with the redis package (createClient and its url option), accessed November 2, 2026