Claude Code + xCloud

Deploy from Git with Claude Code on xCloud

Deploying from Git with Claude Code means telling Anthropic's terminal agent to ship the repository you are already working in, and letting xCloud detect the app, preview the site, create it after your approval and verify the live URL.

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

Set up Claude Code All Claude Code guides

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

git_detectread-only

AgentNode.js 20 app on main. Build: npm run build, start: npm start, web root dist. Suggested URL shop-staging.acme.xcloud.site. One warning: no .env in the repo, so I will pass NODE_ENV=production. Create it?

YouYes.

servers_sites_git_autoneeds approval

AgentQueued. Cloning, installing, building, issuing SSL... deployed. https://shop-staging.acme.xcloud.site answers 200. Push-to-deploy is available since the repo is on your connected GitHub; want it on?

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 Claude Code to Deploy from Git on xCloud?

Connect Claude Code 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 type /mcp inside Claude Code, pick xcloud and choose Authenticate. The browser opens on the xCloud approval screen, where you tick the teams and choose Read-only or Full access.
Terminal
```
claude mcp add xcloud --transport http https://app.xcloud.host/mcp
```
2
Install the xCloud skills plugin
Optional but recommended. Inside Claude Code, add the xCloud marketplace, install the plugin and reload. The nine skills teach Claude Code which tool to reach for, how to dry-run and confirm, how to poll a long job and how to diagnose a failed deploy.
Terminal
```
/plugin marketplace add xCloudDev/xcloud-agent-skills
/plugin install xcloud@xcloud-agent-skills
/reload-plugins
```
3
No browser? Use an API key
For a headless or CI 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 pass it as a header. Keep the single quotes: xCloud tokens contain a pipe character.
Terminal
```
claude mcp add xcloud --transport http https://app.xcloud.host/mcp \
  --header 'Authorization: Bearer YOUR_TOKEN'
```

Check it worked

Then ask Claude Code for the job itself, for example:

Prompt

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

In practice

How Does Deploy from Git Work from Claude Code?

Claude Code sits in the project directory, so it already knows the remote URL, the branch you are on and the scripts in package.json or composer.json. When you say deploy this, it does not need you to paste a repository address; it reads the remote, calls xCloud's detection with the server you named, and compares what xCloud suggests for install, build and start commands with what the repository actually declares. If the two disagree, it says so before anything is created. That is the difference between deploying from inside the codebase and deploying from a dashboard form: the agent can check the build command against the real scripts table instead of trusting a default.

The flow in the terminal is short. You ask, Claude Code runs git_detect and reports the app type, branch and warnings in a few lines. It asks xCloud for a free staging hostname unless you named a domain, then sends the create request as a dry run and prints the would_create summary: the URL, the runtime version, the commands and the web root. You answer yes once. Claude Code sends the same body with confirm set to true and an idempotency key, then polls the site status, printing one line per real step change rather than one per poll. When the state is terminal it reads failed_steps and the SSL block, fetches the URL, and only then tells you the site is live, with the dashboard link xCloud returned.

With the xCloud skills plugin installed, the xcloud:deploy skill adds the judgement around those calls: it refuses to pick a server silently, it treats a repository access error as something to fix with a deploy key rather than something to bypass, and when a deploy fails it goes straight to the diagnosis, proposes a change to the build command or web root, and retries on the same site after you approve. Because Claude Code can also edit files, a failing build can be fixed in the repository, committed and redeployed in the same conversation.

Claude Code specific: Claude Code runs the deploy from whichever directory it was started in. If you open it in a monorepo, name the repository and the branch explicitly, or it will detect the root package and deploy that. The xCloud skills' REST fallback is GET-only in v4.4.2, so the create call always goes through the MCP connection; if you only installed the plugin and skipped claude mcp add, Claude Code can detect and dry-run but will stop at the create step and tell you to connect MCP.

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 Claude Code 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 Claude Code 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 Claude Code 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 repository to my Frankfurt server on a staging hostname. Show me the dry run first.

Prompt

The build failed on xCloud. Read the deploy diagnosis, fix whatever is wrong in the repo, commit it and retry on the same site.

Prompt

Deploy the feature/checkout branch as a staging environment of the API site and give me the URL when it answers 200.

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.

Claude Code and Deploy from Git: Frequently Asked Questions

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

Can Claude Code deploy a repository without me giving it the URL?

Yes. Started inside the project, it reads the Git remote and the current branch. You still choose the server, or let it list provisioned servers and ask, and you approve the dry run before xCloud creates the site.

What if the build fails after Claude Code deploys?

Claude Code reads xCloud's deployment diagnosis, which names the failing step and quotes the log lines, then proposes a fix. Because it can edit files, it can correct the repository, commit, and retry the deployment on the same site after you approve.

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