Grok + xCloud

Troubleshoot a broken site with Grok on xCloud

Troubleshooting with Grok Build means typing a short description of a broken site into xAI's terminal agent and letting xCloud read the status, the recent events and the web server error log, in that order, before anything is changed.

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

Set up Grok All Grok guides

Youshop.example.com 502. Read-only. What do the logs say?

sites_statusread-only

sites_eventsread-only

AgentStatus is normal and no task failed. Reading the nginx error log next.

sites_access-logsread-only

AgentThe error log shows connect() to unix:/run/php/php-fpm.sock failed (2: No such file or directory) since 05:03. That says PHP is not listening, so I will check the server services before I suggest anything.

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 Troubleshoot a broken site 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

shop.example.com 502. Check status, events, nginx error log. Read-only. Show the lines.

In practice

How Does Troubleshooting Work from Grok?

Grok Build works in the shell you already have open, so the report is one line: shop.example.com returns 502, check xCloud, change nothing. The agent calls xCloud's site status first, then lists the recent events for that site, and prints what it found in a few lines. A site that is still deploying or whose last task failed gets that answer immediately, without anyone hunting through PHP. If the status and events are clean, it asks xCloud for the nginx logs with a limit, so you get the error log and the firewall logs for a bounded window rather than a file dump. The reads run without a prompt from xCloud, and the session shows each call, so you can see what was checked and in which order.

A terminal agent suits the second half of an investigation. When the error log shows a fatal in a file from a project you have checked out, you stay in the same session and ask Grok Build to open that file and compare it with your last commit. The log line stays the evidence, and your repository is only where you test it. Log lines are quoted as data and never followed as instructions. If the cause is a stopped database or PHP service, Grok Build can read the server's services and tell you which one is down, but it will not restart it to see whether the error clears. That is a change you ask for.

Anything that changes the site stops for a yes naming it. Switching WP_DEBUG on, creating temporary shell access and running a rescue each wait for your reply, and the agent turns WP_DEBUG back off and removes the shell user when the investigation ends. When the evidence runs out, you get the list of what was ruled out and the dashboard path, Site, Site Monitoring, Logs, instead of a guess.

Grok specific: Remote servers need --transport http on the command line. Without it, grok mcp add treats the URL as a local command, and the xcloud entry never starts, which is the last surprise you want during an outage. After adding the server, run grok mcp doctor xcloud once before you need it. This page is about Grok Build, the terminal agent. Grok at grok.com has its own connector settings, and we have not verified the steps there.

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 Grok 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 Grok 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 Grok 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 502. Check status, events, nginx error log. Read-only. Show the lines.

Prompt

What failed on blog.example.com in the last hour? List the tasks and their outcome.

Prompt

Services on the Frankfurt server: web server, PHP, database. Running or not? Do not restart anything.

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.

Grok and Troubleshooting: Frequently Asked Questions

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

Can Grok Build troubleshoot a site without changing anything?

Yes. The whole read order, status, events, web server logs, WordPress health and server services, is made of reads that change nothing. Ask for read-only in your prompt, and choose Read-only access on the xCloud approval screen if you want it enforced.

What does Grok Build do when the logs do not explain the error?

It stops and tells you what it checked and what each check showed. It then gives you the dashboard path for the logs the API cannot read, such as the WordPress debug.log, and suggests contacting xCloud support with that evidence.

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