Gemini CLI × OpenBerth

Deploy from Gemini CLI

Gemini CLI's MCP schema uses `httpUrl` (not `url`). One settings.json edit and Google's coding agent can push apps to your box.

  • Live in 30 seconds
  • Your domain
  • No per-app bills
Quickstart

Connect Gemini CLI in under a minute

Gemini CLI reads ~/.gemini/settings.json on launch. Add the OpenBerth server entry and you're live.

  1. Install the CLI.
    Terminal
    npm install -g @google/gemini-cli
  2. Open ~/.gemini/settings.json and add the OpenBerth entry. Note the field name is httpUrl, not url — Gemini's schema differs from Cursor's.
    ~/.gemini/settings.json
    {
      "mcpServers": {
        "openberth": {
          "httpUrl": "https://yourdomain.com/mcp",
          "headers": {
            "Authorization": "Bearer bt_your_api_key"
          }
        }
      }
    }
  3. Run gemini and ask it to deploy: “ship this project through OpenBerth.”

Replace yourdomain.com with your server’s URL and bt_your_api_key with an API key from your workspace’s People page.

What you can do

Ask Gemini CLI, OpenBerth handles it

Ship in one sentence

Ask the AI to deploy and it does. Real HTTPS URL in seconds, no dashboard tab-hopping.

Iterate in a sandbox

Push live edits to a sandbox berth. Promote when it's right, throw it away when it isn't.

Roll back any release

Every deploy is versioned. One command (or one ask) and you're back to the last good build.

Manage secrets in plain English

Set, list, rotate, delete — your env vars stay on your server, never in the chat transcript.

Why your own server

OpenBerth handles hosting, so you handle creating

It's yours. Forever.

Your apps live on a server you own. Nobody else holds your code, your domain, or your customer data.

No surprise bills

Pay your server's flat monthly fee. Ship one app or a hundred — the price doesn't change.

Built for real apps

Databases, file uploads, background jobs, custom domains. The boring stuff that makes a website feel like a real product.

Every AI ships to one place

Lovable, Cursor, Claude, Gemini — they all push to the same dashboard. One place to see what's live.

FAQ

Common questions

  • Why httpUrl instead of url?
    Gemini CLI's MCP schema distinguishes between stdio and HTTP transports by the field name. `httpUrl` tells it to speak HTTP. Other clients (Cursor, Claude) use `url` — same value, different key.
  • Does Gemini CLI support OAuth for MCP servers?
    Not yet. You authenticate with the Bearer token from your OpenBerth API key, same pattern as Cursor or Claude Code.
  • How do I see which MCP servers are loaded?
    Inside a Gemini CLI session run `/mcp` — it lists every connected server and their tool count.
  • Can I run Gemini CLI inside CI?
    Yes. Set GEMINI_API_KEY and the OpenBerth Bearer token via env vars or a settings.json mounted into the CI container. The CLI is fully scriptable.
  • Gemini CLI says it can't reach the server — what now?
    Two usual suspects. First, your `httpUrl` ends in `/mcp` (not just the workspace URL). Second, your Bearer token doesn't have a stray newline. Run `/mcp` inside Gemini and read the actual error — it tells you which one.

Ready to ship from Gemini CLI?

Stand up a server in minutes, paste the snippet above, and your AI tool can deploy on its own.