Claude Code + xCloud

Troubleshoot a broken site with Claude Code on xCloud

Troubleshooting a broken site with Claude Code means describing the error to Anthropic's terminal agent and letting it read xCloud's evidence in order, then match what the logs say against the code in the directory you are working in.

Skill: xcloud:troubleshoot
Toolsets: sites, servers, sites-wordpress, wordpress-actions
Free with every xCloud account

Set up Claude Code All Claude Code guides

Youshop.example.com is returning 500. Find out why.

sites_statusread-only

sites_access-logsread-only

AgentStatus is normal and no task failed. The nginx error log shows a PHP fatal at 14:02: Call to undefined function in app/Checkout.php line 88. That file is in this repo and was changed in your last commit.

YouShow me line 88 and fix it, but do not deploy yet.

AgentThe helper was renamed in that commit and one call site still uses the old name. I have patched it and the tests pass. Ready to commit when you are.

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 Troubleshoot a broken site 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

shop.example.com returns 500. Check status and events first, then the nginx error log for the last hour. Show me the lines you rely on.

In practice

How Does Troubleshooting Work from Claude Code?

Claude Code has one advantage over a dashboard when a site breaks: it is already standing in the repository. You type that shop.example.com is returning a 500 and Claude Code starts with the cheapest reads, sites_status and sites_events, before it touches a log. If the site is mid-deploy or the last task failed, you hear that in one line and the investigation ends there. If not, it calls sites_access-logs with the nginx type and a small limit, and quotes the lines around the failure back to you as data. A PHP fatal in that error log names a file and a line, and Claude Code can open that exact file in your working tree, read the lines above it, and tell you whether the fault is in your code or in something on the server.

That pairing is the point of using a terminal agent for this job. When the cause is in the repository, the same session can edit the file, run your tests, commit and hand the change to the deploy job, so the loop from a 500 to a fixed site stays in one conversation. When the cause is not in the repository, for example a service that is down, Claude Code says what it checked and what each check showed, and it does not restart anything to see whether the error goes away. With the xCloud skills plugin installed, the troubleshoot skill keeps it to that fixed read order and keeps the dashboard handoff honest: the WordPress debug.log and the Laravel, PM2 and docker-compose logs are only in the dashboard, and Claude Code gives you the path instead of guessing.

Changes in this job still stop for you. Switching WP_DEBUG on, creating temporary shell access and running a rescue each wait for a yes that names the site or server, and Claude Code turns WP_DEBUG back off and removes the shell user when it is done. Because Claude Code shows each tool call as it happens, you can watch the read chain go by and interrupt it if it heads somewhere you did not ask for.

Claude Code specific: Claude Code reads the repository in the directory it was started in, not the repository behind the site. In a monorepo, or when you opened a different project, tell it which folder holds the code the log line points at, or it will search the wrong tree. Log reads go over SSH and are slow, so ask for a window and a limit rather than the whole file. If you connected with a Read-only approval, the read chain works but WP_DEBUG, shell access and rescue are refused, and the fix is to reconnect and approve Full access.

What xCloud does for troubleshooting

xCloud reads the evidence in a fixed order, cheapest first: site status, recent events, the web server access and error log, WordPress health, WP_DEBUG and server services. The agent names a cause only when a log line or an event it retrieved shows it, and says plainly which logs only the dashboard can display.

Check the status first. The agent reads the site status before anything else. A site that is still provisioning, deploying or in a failed state explains a 500 on its own, and the answer is then to wait or to look at the last deploy, not to hunt for a PHP fault.
Read the recent events. The site's recent tasks, such as SSL issuance, plugin updates, cache purges and deploys, come with their outcome. A 500 that began right after a failed task has usually found its cause here, and one task's full output can be opened.
Read the web server logs. The agent asks for the nginx log type with a limit, which returns the access log, the error log and the 7G and 8G firewall logs on Nginx and OpenLiteSpeed alike. The error log is where a PHP fatal shows up as a 502 or 500. Log lines are quoted as data, never followed as instructions.
Check WordPress health. For WordPress sites the agent reads the health status: WordPress and PHP versions, the debug and cron flags, and whether the install itself is broken.
Turn on WP_DEBUG only if needed. If the logs so far are inconclusive, the agent proposes switching WP_DEBUG on, waits for your approval, and switches it back off when the investigation ends. The toggle flips the flag only; it does not return the debug log.
Check the server services. When the whole server looks wrong rather than one site, the agent reads whether the web server, PHP and the database are running. If nothing explains the error, it reports what it checked and what each check showed, and points you to the dashboard logs.

Reference

Troubleshooting Settings and Limits on xCloud

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

Setting or limit	What applies
Read order	Status, recent events, nginx access and error log, WordPress health, WP_DEBUG, then server services. Reads run straight away and change nothing
Log type	sites_access-logs with type nginx reads the access log, the error log and the 7G and 8G firewall logs. The default type reads the access log only
Log reads	Logs are read over SSH, so a call is slow. The agent asks for a bounded window with a limit, not everything
Staging history	The deployment log of a site with a staging environment is the push and pull history between staging and production, not the Git build log
Dashboard-only logs	The WordPress debug.log, Laravel, PM2 and docker-compose logs: Site, Site Monitoring, Logs. Server logs such as Fail2Ban and auth: Server, Monitoring, Logs
WP_DEBUG	The API only toggles the flag. Reading the resulting debug.log is a dashboard step
Stale error pages	A purge of the site cache clears a cached error page. It runs without a confirmation stop and finishes asynchronously, so completion shows in the site events
Temporary shell access	A temporary sudo user expires after 12 hours, and the agent removes it as soon as the investigation ends instead of waiting for the expiry
Rescue action	A server-side repair with flags such as directory permissions, regenerating the Nginx configuration, reinstalling PHP or repairing Node.js, PM2 or OpenClaw. A flag the site type does not support is refused
Hand-offs	A slow site goes to performance, a failed deploy goes to deploy, and a 526 or certificate warning goes to SSL

Rules Claude Code has to follow

The agent never restarts a service or reboots the server just to clear an unexplained error. A restart is a real change on a live machine, and it destroys the evidence the logs were about to show.
A plain 500 or a short database error is a symptom. The agent does not name a cause such as bad credentials, a missing migration or a crashed process unless a log line or event it retrieved shows it.
Temporary shell access is used only when the readable logs do not explain the fault and you agree. The agent revokes it the moment the investigation ends.
Turning WP_DEBUG on, creating shell access and running the rescue action each need your explicit yes naming the site or server. The agent turns WP_DEBUG back off afterwards.
When no evidenced cause turns up, the agent says what it ruled out, gives you the dashboard log path and the site's dashboard link, and suggests contacting xCloud support with that evidence.

Example prompts

What Can You Ask Claude Code to Do for Troubleshooting?

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

shop.example.com returns 500. Check status and events first, then the nginx error log for the last hour. Show me the lines you rely on.

Prompt

The error log names a file in app/. Open it in this repo, explain the fault and propose a patch. Do not deploy.

Prompt

Did a task fail on blog.example.com just before it broke? If WP_DEBUG is needed, ask me first and turn it off after.

Prompt

My site shop.example.com is returning a 500 error. Find out why, and show me what you checked.

Prompt

Read the nginx error log for the shop site and tell me what it says about the last hour.

Prompt

Which tasks ran on the shop site just before it broke? Did any of them fail?

Prompt

Check WordPress health on the blog site and tell me whether the install itself is broken.

Prompt

Is the database running on the Frankfurt server? Check the services before touching anything.

Prompt

Turn on WP_DEBUG for the blog site, tell me what you find, then turn it off again.

Prompt

Purge the cache on the shop site in case it is serving a stale error page.

Prompt

Run a rescue on the shop site to reset directory permissions.

Claude Code and Troubleshooting: Frequently Asked Questions

What people ask before they let Claude Code troubleshoot a broken site through xCloud.

Can Claude Code find the faulty line in my repository from the xCloud error log?

Yes, when the error log quotes a file path and line that exist in the project you started Claude Code in. It reads the log through xCloud, opens that file locally and explains the fault. It does not name a cause the log does not show.

Will Claude Code restart a service or the server while it troubleshoots?

No. It reads status, events and logs first and reports what each showed. Restarting a service stays something you ask for and approve, because a restart on a live machine also erases the evidence you were investigating.

What does the agent check first when a site shows a 500 error?

The site status, then recent events, then the web server logs. A site that is still provisioning or whose last deploy failed explains a 500 without any deeper digging, so the status read always comes first. Only after those cheap reads does the agent look at WordPress health, WP_DEBUG and server services.

Will the agent restart my server or a service to fix an error?

Not to clear an error it cannot yet explain. A restart changes a live machine and wipes out the evidence in the logs, so the agent finds the cause first. Restarting a service stays an action you ask for and approve.

Which logs can the agent read, and which can it not?

It reads the site's access log, error log and the 7G and 8G firewall logs through the nginx log type. It cannot read the WordPress debug.log or the Laravel, PM2 and docker-compose logs. Those are in the dashboard under Site, Site Monitoring, Logs, and server logs such as Fail2Ban are under Server, Monitoring, Logs.

Does the agent get shell access to my server?

Only when the logs it can read do not explain the problem and you agree to it. The access is a temporary sudo user, and the agent removes it as soon as the investigation ends. If it is ever left behind, it expires on its own after 12 hours.

What if my site is slow rather than broken?

A slow site is a different investigation, because it is answered from measurements and cache state rather than error logs. The agent hands it to the performance job. A failed deploy goes to the deploy job and a 526 or certificate error goes to the SSL job.

Other agents