Claude + xCloud

Troubleshoot a broken site with Claude on xCloud

Troubleshooting a broken site with Claude means telling the chat assistant what the visitor sees, then letting it read xCloud's status, events and web server logs through your custom connector and explain the cause in plain language.

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

Set up Claude All Claude guides

YouThe shop at shop.example.com shows a critical error. What happened?

sites_eventsread-only

AgentA plugin update on shop.example.com failed at 07:41 and the site has erred since. I will read the error log to confirm.

sites_access-logsread-only

AgentThe error log shows a PHP fatal from that plugin's main file right after the update. That fits the failed task. I can purge the cache once you have rolled the plugin back, or look at WordPress health first.

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 to Troubleshoot a broken site on xCloud?

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

1
Add xCloud as a custom connector
In Claude, open Customize, then Connectors, and choose Add custom connector. Name it xcloud, paste this URL as the remote MCP server URL and finish the setup. Claude shows the xCloud sign-in page; choose the teams and Read-only or Full access.
URL
```
https://app.xcloud.host/mcp
```
2
Check the connection
Start a new chat, check that the xcloud connector is enabled for it, and ask this. Claude calls xCloud and names your account and the teams you approved.
Prompt
```
Who am I on xCloud?
```
3
On Team or Enterprise, add it as an owner
Members cannot add custom connectors on a Team plan. An Owner or Primary Owner adds it under Organization settings, then Connectors, with the same URL. On Enterprise, a custom role with Manage access to Libraries can add it too.
URL
```
https://app.xcloud.host/mcp
```

Check it worked

Then ask Claude for the job itself, for example:

Prompt

My shop at shop.example.com has shown a critical error since this morning. Check what xCloud knows about it and tell me the most likely cause, with the evidence.

In practice

How Does Troubleshooting Work from Claude?

Most people reach for Claude in a browser tab, often with the broken page open in the next one. That shapes how this job goes. You write that the shop at shop.example.com shows a critical error since this morning, you may paste the text of the error page or attach a screenshot, and Claude uses that as the starting point for the read chain. It checks the site status with sites_status, lists recent tasks with sites_events and, if neither explains the failure, reads the nginx error log with sites_access-logs. It answers in sentences, quotes the log lines it relied on, and says which step it is on while a slow log read is running.

Nothing in this conversation touches your machine. Claude has no view of your repository or your terminal, so the answer is always about the server side: a failed plugin update, a cached error page, a PHP fatal that the error log attributes to a plugin, a database service that is not running. When the log points at your own code, Claude can explain the stack trace you paste back and describe the fix, but applying it is a job for a coding agent or for you. That boundary is useful for someone who manages sites without being a developer, such as an agency owner or support lead, because the output is a plain finding with evidence and a next step rather than a diff.

Approvals appear in the chat. Reads run straight away, and anything that changes the site, such as switching WP_DEBUG on, creating temporary shell access or running a rescue, waits for you to say yes in the conversation with the site named. When a log cannot be read from here, the WordPress debug.log for example, Claude gives you the dashboard path and the site's dashboard link instead of implying it looked.

Claude specific: Claude reaches xCloud from Anthropic's cloud through the custom connector, so the connector has to be enabled for the chat you are in, and a Free plan allows only one custom connector in total. If Claude answers that it cannot see xCloud, open Customize, then Connectors, and check that xcloud is listed and still signed in. Chat is also the wrong place for a repository fix: Claude can explain a stack trace you paste, but it cannot open your code. Log reads are slow because they go over SSH, so a long wait on the error log step is normal.

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 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 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 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

My shop at shop.example.com has shown a critical error since this morning. Check what xCloud knows about it and tell me the most likely cause, with the evidence.

Prompt

Here is the text of the error page I get on blog.example.com. Read the nginx error log for the last hour and tell me whether the two match.

Prompt

Which tasks ran on shop.example.com before it broke, and did any of them fail? Please do not change anything yet.

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 and Troubleshooting: Frequently Asked Questions

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

Can I paste a screenshot or error message into Claude and have it check my xCloud site?

Yes. The text or screenshot tells Claude what the visitor sees, and it then reads the site's status, recent events and nginx error log through the xCloud connector. It still names a cause only when a log line or event it retrieved shows it.

Does Claude in chat see my code when it troubleshoots a site?

No. It sees what xCloud returns for the site: status, events, logs and WordPress health. If the error log points at your own code, paste the stack trace or use Claude Code to open the repository and make the fix.

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