Deploy a Docker container with your AI, over MCP (2026)
Does your project have a Dockerfile? Connected to while over MCP, your AI deploys it as is, over HTTPS, whatever the language.
By Aloïs Oddon, co-founder of Nextmap. Facts checked on November 19, 2026.
The short version. Over MCP, your AI deploys your Docker container with while, over HTTPS, whatever the language. No server to manage, never as root. What matters, like deleting a database, waits for a person’s approval.
Prerequisites
- A project with its Dockerfile, in any language.
- 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.
Without an account, your AI deploys your app as a trial, in one request. To keep it, open the link it gives you and create your account.
With your account, 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 your app, or “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 writes while.yaml next to your Dockerfile:
apiVersion: while/v1
project: mon-appli
services:
- name: web
port: 8080
health:
path: /
Your Dockerfile builds the image of each version, and your container never runs as root, even if the Dockerfile leaves out the USER line. This one serves a page in Python, on the port it receives in PORT1:
FROM python:3.12-slim
WORKDIR /app
COPY index.html .
USER 1000:1000
CMD ["sh", "-c", "python -m http.server ${PORT:-8080} --bind 0.0.0.0"]

Deploy an image that is already built
You, to your AI: Deploy the image our CI just built.
Your AI deploys the image as is, by its digest, without rebuilding it.
Fix the vulnerabilities in your image
You, to your AI: Fix the vulnerabilities in our image.
The packages in your image, system packages included, are checked against known vulnerabilities at every deployment, then every day. Your AI is warned about a serious vulnerability, and updates your image.
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. It is backed up every day, and can go back to a precise moment if needed.
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.
Move to your own domain
You, to your AI: Put the app on planning.acme.com.
Your AI declares the domain, you add the DNS records it gives you, and the HTTPS certificate follows.
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: Web service, Prebuilt image, PostgreSQL databases, Scheduled jobs, Internal access and Custom domain.
Next steps
Sources
- Docker, the Dockerfile reference (CMD, exec form and variables), accessed November 1, 2026