# How to build a website with Gemini CLI and publish it to your own domain

Add PageHub to Gemini CLI with one command, then describe the site you
want. Gemini builds it, checks it with screenshots, and puts it on your
domain. You end up with a real site that anyone can edit visually, not a
folder of code you still have to host.

**Signed in with a Google account?** Since June 18, 2026, Gemini CLI no
longer works with a free, Google AI Pro, or Ultra sign-in. Google moved
those users to Antigravity. Follow the Antigravity guide at
pagehub.dev/build-website-with-antigravity instead.

Gemini CLI still works with a paid Gemini API key or a company Gemini
Code Assist license. If that's you, the steps below still apply.

**What you need:** Gemini CLI, a free PageHub account, and a domain if you
want one. Without a domain, the site publishes to a pagehub.dev subdomain.

## How it works

PageHub runs an MCP server, which is a set of tools an AI agent can call.
Gemini CLI supports remote MCP servers over HTTP with OAuth sign-in, so
once you add PageHub, Gemini CLI can call tools like `create_site`,
`set_theme`, `screenshot_site`, and `publish_site` for you.

The site lives in PageHub, not in your project folder. PageHub also sends
its own build rules to Gemini CLI when it connects, so you don't paste any
instructions.

## Step 1: Create a free PageHub account

Go to pagehub.dev/signin and enter your email. You'll get a magic link and
a 6-digit code. Use either one to sign in.

The free plan has no credit card and no time limit. It includes 1 published
site, 20 pages per site, and hosting with SSL, and you can connect 1 domain
you own. Connecting Gemini CLI works on every plan.

## Step 2: Add the PageHub MCP server to Gemini CLI

Run this in your terminal:

```bash
gemini mcp add --transport http --scope user PageHub https://pagehub.dev/api/mcp
```

`--scope user` saves PageHub to `~/.gemini/settings.json`, so it's there
in every folder. Without it, Gemini CLI saves it to `.gemini/settings.json`
in the current folder only.

Now sign in. Start `gemini` and type `/mcp auth PageHub`. A PageHub page
opens in your browser. Sign in with your email, then click **Approve** on
the Authorize PageHub screen. There's no API key to paste.

To check it worked, type `/mcp`. PageHub should say **CONNECTED** with its
tools listed under it. Then ask: "List my PageHub sites."

Gemini CLI asks before it runs each PageHub tool. If you'd rather not
approve every call, pick the option to always allow the server.

## Step 3: Prompt Gemini CLI to build the site

Start gemini in a terminal and describe the site. Say
who it's for, which pages you want, and what visitors should do. Real
details (hours, prices, your email) beat placeholders. Swap the bracketed
parts in these prompts for your own.

A local business site:

```text
Use PageHub to build a website for [business name], a [type of business] in [city].
Pages: Home, Services (with prices), and Contact.
Hours: [days and times]. Address: [address]. Phone: [phone].
Add a contact form that asks for name, email, and what they need.
Keep the look [warm and simple / bold / minimal].
Screenshot it on desktop and mobile before you tell me it's done. Don't publish yet.
```

A portfolio:

```text
Use PageHub to create a portfolio site for me. I'm a [job title] in [city].
Home page: a short intro, then a grid of 6 projects, each with a title, a one-line summary, and an image.
Add an About page and a contact section with my email, [you@example.com].
Clean layout with lots of white space. Use stock photos for now and I'll swap in my own.
Show me screenshots before publishing.
```

A landing page for a side project:

```text
Use PageHub to make a one-page site for my side project, [name]: [one sentence on what it does].
Sections: a hero with an email sign-up form, 3 features, a short FAQ, and a footer.
Suggest 3 color palettes and let me pick one before you build.
When it's built, run an SEO check and fix what it finds. Don't publish until I say so.
```

From there, Gemini CLI looks up PageHub's templates and section blocks,
creates the site with `create_site`, sets colors and fonts with
`set_theme`, adds sections, and finds stock photos with `find_image`. Then
it checks its work with `screenshot_site`.

## Step 4: Review the draft and edit it yourself

Everything Gemini CLI builds lands in a draft. Nobody else sees it until
you publish.

Ask for screenshots at any point. `screenshot_site` takes a real browser
screenshot of the draft, one section at a time if you like, and at phone
width (390 pixels). Gemini reads the screenshots itself and fixes what it sees. To look for yourself, open the site in your PageHub dashboard.

To edit by hand, open your PageHub dashboard, pick the site, and click
**Design**. That opens the visual editor. Drag sections around, change
colors and fonts, and rewrite text. Gemini CLI reads the same draft, so it
sees your edits the next time you ask for changes.

Before you publish, ask Gemini CLI to run `audit_seo` and
`audit_accessibility` and fix what they find.

## Step 5: Publish and connect your domain

Ask Gemini CLI: "Connect [example.com] to this site and tell me the DNS
records to add." It calls `set_domain`, which attaches the domain and
returns the records. Add them where you bought the domain:

- The bare domain (example.com) gets an **A** record at `@`.
- A subdomain such as `www` gets a **CNAME** record.
- Sometimes there's also a **TXT** record, to prove you own the domain.

Copy each value exactly as Gemini CLI gives it to you. The values are
specific to your site, so a value from another guide won't work.

PageHub sets up both example.com and www.example.com, and by default sends
www visitors to the bare domain. SSL certificates are issued automatically
and can take a few minutes once DNS is in place.

Then ask: "Is my domain working yet?" Gemini CLI checks with
`get_domain_status`. Connecting a domain doesn't publish the site, so
finish with: "Publish the site." That calls `publish_site`, and the site is
live.

Rather click? The Domains page for your site in the PageHub dashboard shows
the same records.

## Step 6: Make changes later

You have two ways in, and both edit the same draft.

- **From Gemini CLI:** ask, for example, "In my PageHub site [name], add a
  reviews section under Services." Check the screenshot, then say
  "publish."
- **From the editor:** open the site, click **Design**, make your changes,
  and publish.

If a change goes wrong, the site's History page lets you restore an earlier
version of the whole site or one page. The free plan keeps 15 versions.

## Other ways to ship from Gemini CLI

PageHub is one way to publish a website from Gemini CLI. You can also have
Gemini CLI write the site as code in your project, then deploy the code
yourself. That's how most people deploy a website from Gemini CLI today.

- **Vercel or Netlify:** connect your Git repository, and each push builds
  and deploys the site. You add your domain in their dashboard and set DNS
  at your registrar. A good fit when the site is really an app with its own
  code.
- **GitHub Pages:** serves static files straight from a repository. A good
  fit for simple static sites and project docs.

The tradeoff: you own every line and can build anything. You also handle
Git, builds, and DNS yourself, and every text change is a code change.
Someone who doesn't use Gemini CLI can't easily update it. PageHub fits
when you want a site that people can edit visually. It isn't the right tool
for custom app logic.

## Troubleshooting

### PageHub doesn't connect

Type `/mcp` inside Gemini CLI to see each server's status.

- **Asks you to sign in:** type `/mcp auth PageHub`. Run it again if your
  sign-in expires.
- **DISCONNECTED:** run `gemini mcp list` and check the URL is exactly
  `https://pagehub.dev/api/mcp`.
- **Not listed:** you probably added it without `--scope user` in a
  different folder. Run the add command again with it.

### Sign-in doesn't finish

Gemini CLI signs you in through a browser on the same computer, so it
won't work over SSH or in a remote container. In the browser window, sign
in with the email link or the 6-digit code, then click **Approve**.

If the browser sign-in still won't complete, use an API key instead. Create
one at pagehub.dev/dashboard/api-key, set it as `PAGEHUB_API_KEY` in your
shell profile, and change PageHub's entry in `~/.gemini/settings.json` to:

```json
{
  "mcpServers": {
    "PageHub": {
      "httpUrl": "https://pagehub.dev/api/mcp",
      "headers": {
        "Authorization": "Bearer $PAGEHUB_API_KEY"
      }
    }
  }
}
```

### Gemini says a tool isn't available

Servers load when Gemini CLI starts. If you added PageHub while it was
running, quit and start it again, then type `/mcp` to see PageHub's tools.

If you see a rate-limit error, wait a minute. The server allows 120
requests per minute for each sign-in.

### The domain isn't working

- Compare each record at your registrar with what Gemini CLI gave you,
  character for character. A wrong value fails the same way slow DNS does.
- The bare domain needs an A record. It can't be a CNAME.
- If Gemini CLI gave you a TXT record, add it as well as the others.
- DNS changes can take a while to spread. Ask Gemini CLI to check the
  domain again later.
- If the domain is already attached to another Vercel project, remove it
  there first, then ask Gemini CLI to try again.
- Each site takes 1 domain, plus its www version.

Want the full tool list and other clients? See the MCP server docs at
pagehub.dev/developers/mcp, or compare plans at pagehub.dev/pricing.

## FAQ

### Can Gemini CLI host a website?

No. Gemini CLI writes and runs code on your computer, so the site has to
be hosted somewhere else. In this guide PageHub hosts it, with SSL
included. If you have Gemini CLI write the site as code instead, you
deploy that code to a host such as Vercel, Netlify, or GitHub Pages.

### Is it free?

PageHub's free plan costs $0 with no credit card and no time limit. It
includes 1 published site, 20 pages per site, and hosting with SSL, and
you can connect 1 domain you own. Pro is $7 a month per site ($5 billed
annually) and raises the limit to 300 pages. You buy the domain itself
from a registrar.

### Do I need to know how to code?

No. You describe the site in plain words, and Gemini CLI calls PageHub's
tools to build it. No code files are written to your project. The
technical steps are one terminal command and adding DNS records at your
domain registrar, and Gemini CLI tells you exactly which records to add.

### Does this put any files in my project?

Only if you leave off --scope user. Then Gemini CLI saves PageHub to
.gemini/settings.json in the current folder. With --scope user it goes in
~/.gemini/settings.json in your home folder. The site itself is stored in
PageHub. You can export it as static HTML on any plan.

### Can someone who doesn't use Gemini CLI edit the site?

Yes. Every PageHub site opens in a visual editor where you drag sections,
change colors and fonts, and rewrite text. Gemini CLI reads the same
draft, so it sees those edits the next time you ask for changes. You can
invite 1 teammate per site on Free, and unlimited on Pro and up.

### Can I use Claude Code or Cursor instead?

Yes. It's the same server at the same URL, and there are step-by-step
guides for both. A site you start in one, you can keep editing in another.

### Is it safe to let Gemini CLI edit my site?

Every change Gemini CLI makes goes to a private draft, and visitors keep
seeing the published version until someone publishes. Gemini CLI also asks
before it runs each PageHub tool unless you allow the server. If a change
goes wrong, restore an earlier version from the site's History page.

### Are sites built this way good for SEO?

PageHub renders pages to HTML on the server, and each custom domain gets
its own sitemap.xml and robots.txt. Ask Gemini CLI to run audit_seo, which
checks titles, descriptions, headings, image alt text, and link text, then
fix what it finds.

---

Gemini is a trademark of Google LLC. PageHub isn't affiliated with or
endorsed by Google.