Gemini CLI's MCP schema uses `httpUrl` (not `url`). One settings.json edit and Google's coding agent can push apps to your box.
Gemini CLI reads ~/.gemini/settings.json on launch. Add the OpenBerth server entry and you're live.
npm install -g @google/gemini-cli~/.gemini/settings.json and add the OpenBerth entry. Note the field name is httpUrl, not url — Gemini's schema differs from Cursor's.{
"mcpServers": {
"openberth": {
"httpUrl": "https://yourdomain.com/mcp",
"headers": {
"Authorization": "Bearer bt_your_api_key"
}
}
}
}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.
Ask the AI to deploy and it does. Real HTTPS URL in seconds, no dashboard tab-hopping.
Push live edits to a sandbox berth. Promote when it's right, throw it away when it isn't.
Every deploy is versioned. One command (or one ask) and you're back to the last good build.
Set, list, rotate, delete — your env vars stay on your server, never in the chat transcript.
Your apps live on a server you own. Nobody else holds your code, your domain, or your customer data.
Pay your server's flat monthly fee. Ship one app or a hundred — the price doesn't change.
Databases, file uploads, background jobs, custom domains. The boring stuff that makes a website feel like a real product.
Lovable, Cursor, Claude, Gemini — they all push to the same dashboard. One place to see what's live.
Stand up a server in minutes, paste the snippet above, and your AI tool can deploy on its own.