Deploy a Streamlit app from your AI agent, over MCP

Prerequisites

• A Streamlit app, with its requirements.txt.
• An AI agent that works in a terminal: Claude Code, Codex, Cursor or Gemini CLI.

Step 1: Give your agent these instructions

Open your agent in your app’s folder, and paste these instructions into it:

Connect to while with my account (while.sh/agents), then deploy my app.

Without an account, your agent 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 agent 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 agent gives you your app’s address, for example https://mon-tableau.while.cloud, over HTTPS.

What your agent does

It writes while.yaml at the root of your app:

apiVersion: while/v1
project: mon-tableau
services:
  - name: web
    port: 8501
    health:
      path: /_stcore/health

Your app is installed from requirements.txt, where Streamlit is detected, then started with streamlit run, on streamlit_app.py or app.py, on its usual port, 8501¹. There is no Dockerfile and no command to write. The connection with your browser stays open: if it drops, Streamlit reopens it in less than a second, and your session carries on.

Restrict your app to your colleagues

Your agent adds two lines to the service:

    access: internal
    email_domains: [acme.com]

Once your Google Workspace or Microsoft 365 is linked to while, on the Pro plan, your colleagues open it with their usual account, and your code receives their name and email address, with no sign-in page to write.

Read another app’s database

Your agent gives your Streamlit app read-only access to the database of another of your apps: the dashboard reads, and can never write.

Prepare the data every night

Your agent declares a scheduled job that computes the numbers and stores them in a PostgreSQL database. Your Streamlit app displays them right away, with no long computation in the page.

Move to your own domain

Your agent declares the domain, you add the DNS records it gives you, and the HTTPS certificate follows.

Go back to the previous version

In the 30 minutes after a deployment, the previous version comes back in a second. After that, it takes a few seconds. Once the previous version is back, your agent reads what broke in while’s logs, fixes it and deploys again.

In the docs: Scheduled jobs, Internal access, Custom domain and Versions and rollback.

Next steps

• Restrict an internal tool to company accounts
• Run a scheduled job
• Compare Python API hosting