Gemini CLI + xCloud

Deploy from Git with Gemini CLI on xCloud

Deploying from Git with Gemini CLI means telling Google's terminal agent to ship a repository, and letting xCloud detect the app, preview the site, create it once you approve and confirm that the live URL answers.

Skill: xcloud:deploy
Toolsets: sites, servers, integrations
Free with every xCloud account

Set up Gemini CLI All Gemini CLI guides

YouDeploy this repo to Frankfurt on a staging hostname. Dry run first.

mcp_xcloud_git_detectread-only

AgentNode.js app on main. xCloud would run npm run build and npm start from the dist folder, on a free staging hostname. No warnings. Create the site on Frankfurt?

YouYes.

mcp_xcloud_servers_sites_git_autoneeds approval

AgentDeployed. The staging URL answers 200 and the certificate is in place.

Last updated: October 2026. Keep a human in the loop: xCloud stops and asks before anything that creates, deploys, updates, reboots, deletes or buys.

Setup

How Do You Set Up Gemini CLI to Deploy from Git on xCloud?

Connect Gemini CLI once; every job on this account uses the same connection. Then ask in plain words.

1
Add the xCloud MCP server
Run this in your terminal, then start gemini. The --scope user flag writes the server to ~/.gemini/settings.json so it is available in every project; without it, gemini mcp add writes to the current project's .gemini/settings.json and refuses to run from your home directory. The first time it calls xCloud it finds the OAuth endpoints, opens your browser on the xCloud approval screen and asks you to tick the teams and choose Read-only or Full access.
Terminal
```
gemini mcp add --scope user --transport http xcloud https://app.xcloud.host/mcp
```
2
Or edit settings.json
Add this to ~/.gemini/settings.json for every project, or to .gemini/settings.json in one project. This is the entry gemini mcp add writes: url plus type set to http. The older httpUrl key still works, but a url without a type is treated as an SSE server and will not connect. If the browser sign-in does not start, type /mcp auth xcloud inside Gemini CLI.
JSON
```
{
  "mcpServers": {
    "xcloud": {
      "url": "https://app.xcloud.host/mcp",
      "type": "http"
    }
  }
}
```
3
No browser? Use an API key
For a headless machine, create a token with the mcp:invoke scope plus the read abilities for the areas it will use (read:servers and read:sites, with read:billing and read:addons for billing and add-on tools) and the matching write: abilities if it should change things in Settings, Developers, API Tokens and send it in the headers field. Keep the token out of version control, and keep the quotes: xCloud tokens contain a pipe character.
JSON
```
{
  "mcpServers": {
    "xcloud": {
      "url": "https://app.xcloud.host/mcp",
      "type": "http",
      "headers": {
        "Authorization": "Bearer YOUR_TOKEN"
      }
    }
  }
}
```

Check it worked

Then ask Gemini CLI for the job itself, for example:

Prompt

Deploy this repo to my Frankfurt server on a staging hostname. Show me the dry run first.

In practice

How Does Deploy from Git Work from Gemini CLI?

Gemini CLI runs in the directory you start it in, so it can see the repository you are working on, including the remote and the scripts in your project files. You type deploy this to my Frankfurt server, and it calls xCloud's detection through the tools it discovered from the MCP server. Those tools carry a name starting mcp_xcloud_ followed by the operation, so in the terminal you will see lines such as mcp_xcloud_git_detect while it works. Detection creates nothing, and the answer is a short summary of the app type, the branch, the commands xCloud would run and any warnings.

Gemini CLI asks for confirmation before it runs tools that change something, and xCloud has its own rule for the create call, so a deploy has two checkpoints. You approve the tool call in the CLI dialog, and xCloud refuses the create unless it carries an explicit confirmation after you have seen the dry run. Do not set trust to true on the xcloud entry to skip the dialog, because that removes Gemini CLI's own prompts for every xCloud tool. After you answer yes, the agent sends the confirmed request with an idempotency key, follows the site status with one line per real step change, and fetches the address before it calls the site live. It then offers push-to-deploy if the repository sits on a connected provider.

The terminal also suits the recovery path. If the deployment fails, ask Gemini CLI to read the diagnosis and fix it. It can correct a build command or web root on the same site through a retry. If the cause is in your code, it edits the file, you commit and push, and it retries, because xCloud builds from the remote and never from your working tree. On a server with no browser, the OAuth sign-in cannot redirect to your machine, so use the API-key form of the connection. The token needs mcp:invoke plus read:servers and read:sites for the detection and the status reads, and write:sites for the create itself; a token with mcp:invoke alone reaches the server but every xCloud call is refused.

Gemini CLI specific: Gemini CLI names xCloud tools mcp_xcloud_ followed by the operation, which is why the deploy calls look longer in the terminal than in other clients. Write the xcloud entry as url plus type set to http, the form gemini mcp add writes, because a url with no type is treated as an SSE server and will not connect, and leave trust off so Gemini CLI keeps confirming tool calls. The browser sign-in redirects to a localhost port, so on a remote or headless host use the API-key form.

What xCloud does for deploy from git

xCloud detects the app in the repository, previews the site it would create with a dry run, creates it once you approve, polls the deployment to a terminal state and checks the live URL. A failed deploy gets a diagnosis and a corrected retry on the same site, never a delete and recreate.

Pick the team and server. The agent uses the server you name. If you name none it lists provisioned servers and asks; it never picks one silently. Node.js, PHP and static builds need an Nginx or OpenLiteSpeed server; anything else needs a Docker server.
Detect the repository. git_detect reads the default branch, the app type (WordPress, Laravel, custom PHP, Node.js or Lovable), the web root, suggested install, build and start commands, repository access and server compatibility. Detection creates nothing.
Choose the address. With no domain the agent asks xCloud for a free staging hostname. With a live domain it checks whether the zone is on a connected Cloudflare account, in which case xCloud writes the DNS record and certificate itself.
Dry run, then one approval. The agent sends the create request with dry_run set to true and shows you the resolved configuration: app type, URL, branch, commands, runtime version and every warning. Then it asks once, naming the server and the URL, before sending the same body with confirm set to true and an idempotency key.
Poll and verify. A 202 means queued, not deployed. The agent polls the site status until it is terminal, reports each real step change, reads failed_steps and the SSL block, and fetches the URL before it calls the site live.
Recover if it fails. On a failed deploy the agent reads the deployment diagnosis, proposes a fix from the correctable fields, and retries on the same site with your approval. Two failed retries with the same classification stop the loop and hand you the dashboard link.

Reference

Deploy from Git Settings and Limits on xCloud

The facts Gemini CLI works within when it deploys from Git. Where a row names the dashboard, that step stays yours to take there.

Setting or limit	What applies
Supported app types	WordPress, Laravel, custom PHP, Node.js and Lovable on native servers; Dockerfile and Compose apps, including Python, Go and Rust, on Docker servers
Repository sources	Public HTTPS URLs, repositories on a connected GitHub, GitLab or Bitbucket provider, and private SSH repositories with a read-only deploy key
Private repositories	The agent prepares a deploy key on the server, you add the public key to the repository, xCloud verifies it. A private key or personal token never goes in the request
Preview	dry_run: true returns the would_create block and consumes no idempotency key
Idempotency	The create call carries an Idempotency-Key, so a retried request cannot create a duplicate site. A new deployment needs a new key
Deployment states	deployed, failed or cancelled once terminal is true; failed_steps can be non-empty on a deployed site and must be read
Node.js versions	The Node version is server-wide, not per site; changing it can affect other apps on the server
Redeploys	A redeploy runs git reset --hard and git clean -df in the site directory, so uncommitted server-side changes are lost. Supply environment values through env_file_content, not files in the checkout
Staging environments	Available for Git sites on paid plans through the API; WordPress staging stays a dashboard step
Agentic servers	An OpenClaw, Hermes, Paperclip or DeepSeek Harness server hosts only the site created at provisioning; a second site is refused

Rules Gemini CLI has to follow

Creating a site is billable and stops for your approval; detection and the dry run never create anything.
The agent explains every detection warning before asking, and a repository access problem is never worked around by naming an app type by hand.
A deployed state is not proof the application works: the agent fetches the URL and reads failed_steps first.
A failed site is retried in place with corrections; it is never deleted and recreated to retry.
Changing a live site's domain after creation, databases and server resizing are dashboard steps; the agent gives you the path and the dashboard link xCloud returned.

Example prompts

What Can You Ask Gemini CLI to Do for Deploy from Git?

Type these as written and swap in your own repository, site and server names. Reads and routine actions such as backups, cache purges, PageSpeed scans and vulnerability scans run straight away; creating, deploying, updating, rebooting, deleting, buying or starting a broken-link scan stops and asks first.

Prompt

Deploy this repo to my Frankfurt server on a staging hostname. Show me the dry run first.

Prompt

The last xCloud deploy of the shop site failed. Read the diagnosis, fix the build command and retry on the same site.

Prompt

Detect github.com/acme/api and list which services and ports xCloud would use. Create nothing.

Prompt

Deploy https://github.com/acme/shop to my Frankfurt server and show me the dry run before creating anything.

Prompt

Deploy the private GitLab repository connected to my team on a staging hostname.

Prompt

Scan the docker-compose.yml in github.com/acme/api and tell me which services and ports xCloud would use.

Prompt

Create a staging environment from the feature/checkout branch of the API site.

Prompt

Deploy the latest commit of the shop site after showing me what will change.

Prompt

The last deploy of the API site failed. Diagnose it, fix the build command and retry on the same site.

Gemini CLI and Deploy from Git: Frequently Asked Questions

What people ask before they let Gemini CLI deploy from Git through xCloud.

Why do the xCloud tools have long names in Gemini CLI?

Gemini CLI prefixes each tool with mcp_ and the server name, so git_detect appears as mcp_xcloud_git_detect. The prefix keeps tools from different servers apart and does not change what the tool does.

Can Gemini CLI deploy from a server with no browser?

Yes, with an API key. The OAuth sign-in redirects to a localhost port and needs a browser on the same machine, so on a headless host send a token with the mcp:invoke scope plus read:servers, read:sites and write:sites in the headers field of the xcloud entry and keep the token out of version control.

Does the agent create the site as soon as I give it a repository URL?

No. It detects the repository and runs a dry run first, shows you the resolved configuration, and asks once. Only after you approve does it send the create call with an explicit confirmation and an idempotency key.

Can an agent deploy a private repository through xCloud?

Yes. Either the repository is on a Git provider connected to your xCloud team, or the agent prepares an SSH deploy key on the server for you to add to the repository. A private key or a personal access token is never sent in the request.

What does a 202 response mean during a deploy?

That xCloud queued the deployment. The agent polls the site status until it is terminal and reports deployed, failed or cancelled, then checks failed_steps and fetches the URL before calling the site live.

What happens when a deploy fails?

The agent reads the deployment diagnosis, which classifies the failing step and quotes the relevant log lines, proposes a fix from the fields xCloud lets it correct, and retries on the same site after your approval. It never deletes and recreates the site to retry.

Which servers can take a Git deploy?

Node.js, PHP and static builds deploy to Nginx or OpenLiteSpeed servers. Dockerfile and Compose apps, and other language stacks, need a Docker server. Agentic servers running OpenClaw, Hermes, Paperclip or DeepSeek Harness take no additional sites.

Other agents