Claude Code + xCloud

Manage servers with Claude Code on xCloud

Managing servers with Claude Code means asking Anthropic's terminal agent to read your xCloud servers, change their services, runtimes, cron jobs and firewall rules, and reboot them with proof, from the same session where you edit the code that runs on them.

Skill: xcloud:servers
Toolsets: servers, alerts, user
Free with every xCloud account

Set up Claude Code All Claude Code guides

YouReboot the staging server and tell me when xCloud confirms it is back.

servers_indexread-only

AgentTwo servers match staging. I mean staging-fra (Frankfurt, 3 sites). Rebooting it takes those sites offline for a minute or two. Go ahead?

YouYes, staging-fra.

servers_reboots_storeneeds approval

AgentReboot started. I am reading the operation now... xCloud reports a verified new boot. staging-fra is back and its three sites answer.

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 Manage servers 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
```
List my xCloud servers with CPU, RAM and disk, and flag anything above 80% disk.
```

In practice

How Does Server management Work from Claude Code?

Claude Code starts in a project directory, and that is what sets this page apart from a dashboard or a chat window. When you ask about a server, the repository is right there as context. Say you ask whether the Frankfurt server is ready for the Node.js version your project declares. Claude Code reads the engines field in package.json, calls servers_node-versions_index to see what the server has installed, and tells you the gap in a sentence. It will not move the default on its own. The default is server-wide, so every Node site on that server changes with it, and Claude Code says exactly that before it calls servers_node-versions_default and waits for your yes.

Most sessions begin with a read. Type list my servers and flag anything above 80 percent disk, and Claude Code calls servers_index, then servers_monitoring for each server, and prints one line per server. A status such as Low disk space or Reboot Required gets its own line even if the numbers look fine. Changes follow the same pattern: it restates the server, the item and the impact, then asks. For a reboot it calls servers_reboots_store, reads servers_reboots_show until xCloud reports a verified new boot, and prints that result in the terminal. If the answer stays unconfirmed it looks at servers_tasks to investigate instead of rebooting a second time.

You get two layers of approval, which is worth knowing. Claude Code asks whether it may call a tool, and xCloud's own confirmation rule stops the calls that can interrupt a server. With the xCloud skills plugin installed, the xcloud:servers skill keeps that behaviour consistent, including the habit of naming the team and the server before it changes anything. Claude Code can also run without a person at the keyboard. With an API key that carries the mcp:invoke scope plus read:servers, a scheduled job can run the fleet check and print a report, but keep unattended runs to reads, because nobody is there to give a confirmation.

Claude Code specific: A permission prompt in a terminal is easy to approve on autopilot, and Claude Code's prompt confirms that a tool may run, not what it will do to the server. Read the line where the agent restates the server name before you say yes, especially if your team has two servers with similar names or you have granted the connection to several teams. A server in a team you did not tick on the approval screen comes back as not found, so reconnect with /mcp and tick that team rather than assuming the server is gone.

What xCloud does for server management

xCloud lets the agent list your servers, read their monitoring, and manage services, Node.js and PHP versions, cron jobs, firewall rules, Fail2Ban and sudo users. Changes that can interrupt a server stop for your approval, and a reboot is only reported as done after xCloud verifies a new boot.

Pick the team and the server. The agent works on one team at a time and uses the server you name. If a name is missing or matches several servers, it lists them and asks. It always restates which server it is about to change before it changes it.
Read the state first. It reads the server's status, installed services, runtimes and monitoring figures. A status such as low disk space or reboot required is worth surfacing on its own. Monitoring history is a paid-plan feature, so a free plan answers 403.
Say what will change, then ask. For a service, runtime, cron, firewall or sudo change, the agent names the server, the item and the impact, for example that a Node.js default affects every Node site on the server. It waits for your approval when the change could interrupt a service.
Follow the task to the end. xCloud accepts server work and returns before it finishes. The agent reads the server's task list until the task settles and reports the real outcome, not the acceptance.
Reboot with proof. A reboot starts a tracked operation. The agent reads that operation until xCloud reports a verified new boot. If the result is unconfirmed it investigates and never repeats the reboot just to check.
Buy a server only after approval. A new server is billable. The agent checks what you already have, reads the plans and the card on file, shows the plan, region and price, and waits for a yes. It sends the purchase once with an idempotency key so a retry cannot buy a second server.

Reference

Server management Settings and Limits on xCloud

The facts Claude Code works within when it manages servers. Where a row names the dashboard, that step stays yours to take there.

Setting or limit	What applies
Inventory	Every server on the team with its status, stack and the sites it hosts, plus the tasks, supervisor processes and site snapshots on a server
Monitoring	Current CPU, memory and disk are readable. Monitoring history is a paid-plan feature: xCloud answers 403 on the free plan, which is a plan limit and not a permission
Services	Install, enable, restart and disable. A restart runs without a server-side prompt; the agent still confirms the exact server, service and impact before any service change, because disabling ssh, nginx or a database can lock you out or cause downtime
Node.js versions	Read the installed versions and set the default. The default is server-wide and affects every Node site on the server
PHP versions	Install, uninstall, set the default, patch and toggle OPcache. The server default changes only the command-line php and the version new sites get; it does not change existing sites, and a single site's PHP version is a dashboard setting under Site > Site Settings
Cron jobs	List, create, update, delete, run now and read the last output for server cron jobs. Site cron is a separate resource
Firewall rules	List, create, delete, enable and disable rules with a name, protocol, allow or deny, port and optional source IP
Fail2Ban and IP access	List, ban and unban IP addresses, read the SSH restriction status, and whitelist your current IP or xCloud's own IPs
Sudo users	List, create or update and delete sudo users. A password is a secret and private keys are never returned
Verified reboots	Start a tracked reboot and read its operation; only a verified new boot proves it worked. An unconfirmed reboot can be rechecked without rebooting again
Buying a server	Billable, so it needs an approved plan, region and price, a card on file and an idempotency key. It buys xCloud-managed servers only
Dashboard-only	Resizing or deleting a server, a provider backup of the whole server (Server > Backup), bringing your own server, databases and database users, and PHP settings such as memory limit or upload size

Rules Claude Code has to follow

A change that can interrupt a server stops for your approval, and the agent names the server, the service and the impact first.
Buying a server is billable: the agent shows the plan, region and price and waits for your yes, and it never retries a purchase without checking your server list first.
A reboot is only reported as done when xCloud verifies a new boot, and an unconfirmed reboot is investigated, not repeated.
Disabling ssh, nginx, a database or a runtime service needs your explicit confirmation immediately before the call, because it can lock you out or take sites offline.
Resizing or deleting a server, provider server backups, bringing your own server and per-site PHP versions 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 Server management?

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

List my xCloud servers with CPU, RAM and disk, and flag anything above 80% disk.

Prompt

Check package.json for the Node.js version this repo needs, compare it with the Frankfurt server, and show me what changing the default would affect.

Prompt

Reboot the staging server and tell me when xCloud confirms it is back.

Prompt

List all my xCloud servers with CPU, RAM and disk usage, and flag any server above 80% disk.

Prompt

List the cron jobs on the Frankfurt server with their schedules.

Prompt

Create a server cron job for the WooCommerce Action Scheduler every five minutes. Show me the final command and schedule before creating it.

Prompt

Install Redis on the Frankfurt server and enable the service.

Prompt

Switch the Frankfurt server's default Node.js to the latest LTS major.

Prompt

Reboot the staging server and tell me when it is back.

Prompt

Show me the IP addresses Fail2Ban has banned on the Frankfurt server, and unban 203.0.113.10.

Prompt

Create a new xCloud server on the smallest plan in Singapore. Show me the plan and price first and wait for my approval.

Claude Code and Server management: Frequently Asked Questions

What people ask before they let Claude Code manage servers through xCloud.

Can Claude Code compare my project's Node.js version with the server's?

Yes. It reads the version your repository declares, such as the engines field in package.json, and compares it with the versions xCloud reports as installed on the server. It will tell you the gap but changes the server default only after you confirm, because that default applies to every Node site on the server.

Can I run a server health check from Claude Code without being at the terminal?

Yes, for reads. Run Claude Code non-interactively with an API key that carries the mcp:invoke scope plus read:servers and ask for the CPU, memory and disk report. Do not rely on it for changes, because a reboot, a runtime change or a purchase stops for a confirmation that an unattended run cannot give.

Does the agent ask before it reboots a server?

Yes. A reboot stops for your explicit confirmation, then the agent starts a tracked reboot and reads the operation until xCloud reports a verified new boot. If the result stays unconfirmed it investigates rather than rebooting a second time.

Can an AI agent buy a new server for me?

Yes, but only after you approve it. A new server is billable, so the agent first checks your existing servers, reads the available plans and your card on file, then shows the plan, region and price and waits for your yes. It sends the purchase once, so a retry cannot buy a second server.

If the agent changes the server's PHP default, do my sites change version?

No. The server default changes the command-line php and the version new sites get, and it moves no existing site. Each site keeps its own PHP version, which you change in the dashboard under Site > Site Settings.

Can the agent resize or delete a server?

No. Resizing and deleting a server are dashboard-only, as are a provider backup of the whole server, databases and bringing your own server. The agent can tell you where the control is and give you the server's dashboard link.

Why did the agent say monitoring history is not available?

Monitoring history is a paid-plan feature, so xCloud answers 403 on the free plan. Current CPU, memory and disk readings are still available, and the agent will say that it is a plan limit, not a missing permission.

Other agents