Grok + xCloud

Deploy from Git with Grok on xCloud

Deploying from Git with Grok means running xAI's Grok Build agent in your repository and letting xCloud detect the app, preview the site, create it after your approval and check that the live URL answers.

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

Set up Grok All Grok guides

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

git_detectread-only

AgentNode.js app on main, build npm run build, start npm start. Staging address: app-staging.acme.xcloud.site. No .env in the repo. Create it?

YouGo.

servers_sites_git_autoneeds approval

AgentDeployed. https://app-staging.acme.xcloud.site answers 200. The dashboard link is below.

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 Grok to Deploy from Git on xCloud?

Connect Grok 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 grok. The first time it calls xCloud, a browser opens on the xCloud approval screen, where you tick the teams and choose Read-only or Full access. Add --scope project to save the entry in .grok/config.toml for one repository instead.
Terminal
```
grok mcp add --transport http xcloud https://app.xcloud.host/mcp
```
2
Or edit ~/.grok/config.toml
Add this table to ~/.grok/config.toml, then run grok mcp doctor xcloud to check the connection. The url key is the one for HTTP servers.
TOML
```
[mcp_servers.xcloud]
url = "https://app.xcloud.host/mcp"
```
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. Put it in an environment variable the machine starts Grok with, such as XCLOUD_TOKEN in a systemd EnvironmentFile or your shell profile, and pass a reference to it with --header. Keep the single quotes so the shell leaves ${XCLOUD_TOKEN} alone: Grok expands ${VAR} in headers when it loads the config, so the token itself never lands in your shell history or in config.toml. Run grok mcp doctor xcloud to confirm it works.
Terminal
```
grok mcp add --transport http --header 'Authorization: Bearer ${XCLOUD_TOKEN}' xcloud https://app.xcloud.host/mcp
```

Check it worked

Then ask Grok for the job itself, for example:

Prompt

Deploy this repo to my Frankfurt server on a staging hostname. Dry run first.

In practice

How Does Deploy from Git Work from Grok?

Grok Build is a terminal agent, so a deploy starts where your code is: you change into the repository, run grok and type a line. Because it works from the project directory it can read the Git remote and the branch you are on, which means a request like deploy this repo to my Frankfurt server on a staging hostname does not need a pasted link. It passes the repository to xCloud's detection with the server you named and reports the app type, the commands xCloud would run, the web root and any warning in a few lines of terminal output. Detection creates nothing, so you can ask for it on its own whenever you want to see what xCloud makes of a repository.

Registering the server is a one-liner, and that shapes how you use it. You add xcloud with grok mcp add --transport http, either globally or with --scope project so the entry lives in that repository's .grok/config.toml. Grok Build also loads MCP servers from ~/.claude.json, .cursor/mcp.json and a project .mcp.json, so if xCloud is already set up for another client in the same repository you may be connected already. Check grok mcp list before adding it a second time, and open /mcps in a session to see that xcloud is loaded. From there the flow is the usual one: a dry run, one yes, the confirmed create through servers_sites_git_auto, polling with sites_status, a fetch of the URL and a read of failed_steps before the site is called live.

The terminal also keeps the failure loop short. After a failed build, Grok Build can read xCloud's deployment diagnosis, then open the file the diagnosis points at, such as a build script or an environment example, in the same session. You decide whether the repository or the xCloud build setting should change, and the retry goes to the same site after you approve, never through a delete and recreate.

Grok specific: Without --transport http, grok mcp add treats the URL as a local command, and the xcloud tools never appear, so run grok mcp doctor xcloud if a deploy request finds nothing to call. This page covers Grok Build. If you meant to deploy from a chat at grok.com, there is no checkout there, so paste the repository link, and note that the connector steps in that product are not verified on this page.

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 Grok 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 Grok 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 Grok 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. Dry run first.

Prompt

grok mcp list shows xcloud. Run detection on this repo and list every warning. Create nothing.

Prompt

The deploy failed. Read the diagnosis, show me the file it points at and retry on the same site once I say so.

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.

Grok and Deploy from Git: Frequently Asked Questions

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

Do I have to paste the repository link into Grok Build?

No. Started inside the repository, Grok Build can read the Git remote and the current branch. You still name the server or let it list your servers, and you approve the dry run before xCloud creates anything.

Can I keep the xCloud connection to one repository in Grok Build?

Yes. Run grok mcp add with --scope project and the entry is saved in that repository's .grok/config.toml instead of the global file. Grok Build also reads .cursor/mcp.json and a project .mcp.json, so check grok mcp list for an existing xcloud entry first.

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