ChatGPT + xCloud

Troubleshoot a broken site with ChatGPT on xCloud

Troubleshooting a broken site with ChatGPT means opening a chat with the xcloud developer-mode app selected, describing the error, and having it read xCloud's status, events and nginx logs and explain the evidence in plain language.

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

Set up ChatGPT All ChatGPT guides

YouUsing the xcloud app, why is shop.example.com showing a critical error?

sites_statusread-only

sites_eventsread-only

AgentThe site status is normal, but a plugin update failed at 07:41 and the errors began right after. Shall I read the nginx error log to confirm?

YouYes, last hour only.

sites_access-logsread-only

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 ChatGPT to Troubleshoot a broken site on xCloud?

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

1
Turn on developer mode and open Plugins
In ChatGPT on the web, open Settings, Security and login and turn on Developer mode. Then open the Plugins page and select the plus button to create an app. OpenAI lists developer mode for Pro, Plus, Business, Enterprise and Education accounts on the web, but its help center puts full MCP support with write actions in beta on Business, Enterprise and Edu workspaces and gives Pro accounts read and fetch access only, so check your plan before you expect ChatGPT to deploy or update anything. That path is for a personal account. In a Business, Enterprise or Edu workspace the controls sit under Apps instead. On Business only an admin or owner can use Developer mode: they turn it on while creating the app from Workspace settings, Apps, Create, and publish it from Workspace settings, Apps. On Enterprise and Edu an admin or owner can also toggle Developer mode under Settings, Apps, Advanced settings, and a member granted developer access under Permissions and Roles turns it on there too and can create and test the app from their own Settings, Apps, Create, but only an admin or owner can publish it. An ordinary member cannot do this, so ask an admin to publish the xcloud app; then open Settings, Plugins, select xcloud, install it if offered and choose Connect, sign in to xCloud and pick the teams and access level, and only then start at the last step.
URL
```
https://chatgpt.com/plugins
```
2
Create the app with the xCloud MCP URL
Name the app xcloud, paste this as the MCP server URL and choose OAuth for authentication. xCloud supports dynamic client registration, so you do not need to create a client ID. Sign in with xCloud when the browser asks, tick the teams and choose Read-only or Full access.
URL
```
https://app.xcloud.host/mcp
```
3
Install the plugin and use it in a Work chat
Open your personal Plugins page, open xcloud and select the plus button to install it. Back on the ChatGPT homepage, switch the tab at the top from Chat to Work, start a new Work chat, type @ and pick xcloud; a plain Chat tab conversation does not offer the plugin. Then type a request like this one.
Prompt
```
Using the xcloud app, who am I on xCloud and which servers do I have?
```

Check it worked

Then ask ChatGPT for the job itself, for example:

Prompt

Using the xcloud app, check why shop.example.com shows a critical error. Read status, recent events and the nginx error log, and quote the lines you rely on.

In practice

How Does Troubleshooting Work from ChatGPT?

ChatGPT will not call a developer-mode app unless you pick it, so the job starts by picking it: start a Work chat from the Work tab, type @xcloud to select the plugin, and then describe the problem. A prompt that begins with using the xcloud app keeps the model on the connector instead of answering from general knowledge about 500 errors. You say that shop.example.com is showing a critical error. ChatGPT reads the site status, lists recent events and, if those do not explain it, reads the nginx error log, and it answers with the log lines it relied on and a sentence on what they mean. You can paste the text of the error page or a screenshot to give it something to match.

ChatGPT connects from OpenAI's servers, not from your computer, and it has no access to your repository or terminal. That makes this a good fit for the person who owns the site but not the code: the answer is a finding about the server side, such as a failed task, a cached error page or a PHP fatal attributed to a plugin, plus a next step. When the log points at custom code, ChatGPT can explain a stack trace you paste back, but the fix happens somewhere else. For a stale cached error page the one repair on offer is a cache purge, which runs without a confirmation stop and finishes asynchronously, so ChatGPT checks the site events for completion.

Because OpenAI treats developer mode as higher risk, choose Read-only on the xCloud approval screen for an investigation: every step of the read chain is a read. If you do approve Full access, switching WP_DEBUG on, creating temporary shell access and running a rescue still wait for your explicit yes naming the site or server, and ChatGPT shows its own confirmation for write actions too. Where xCloud can only point you to a dashboard log, ChatGPT gives you the path and the site's dashboard link rather than pretending it read it.

ChatGPT specific: Pick the plugin with @xcloud in each new Work chat, or ChatGPT will answer from general knowledge instead of reading your site. Developer mode is documented for ChatGPT on the web, and this job suits every plan that has it, because status, events and logs are reads, which OpenAI's help center allows even on Pro, where write actions are not available. The app sits under Drafts in settings, where you can switch individual tools off and refresh the list. Choose Read-only on the xCloud approval screen for troubleshooting, since status, events and logs are all reads. Log reads go over SSH, so a pause 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 ChatGPT 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 ChatGPT 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 ChatGPT 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

Using the xcloud app, check why shop.example.com shows a critical error. Read status, recent events and the nginx error log, and quote the lines you rely on.

Prompt

Using the xcloud app, did any task fail on blog.example.com before it broke? Do not change anything.

Prompt

Using the xcloud app, is the site serving a stale cached error page? Check the logs first, and ask me before you purge the cache.

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.

ChatGPT and Troubleshooting: Frequently Asked Questions

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

Why does ChatGPT answer with general advice instead of reading my xCloud site?

The xcloud app was probably not selected for that chat. Pick the xcloud plugin with @xcloud in a Work chat, and start the prompt with using the xcloud app. Then it calls status, events and the nginx logs for your site.

Is Read-only access enough for ChatGPT to troubleshoot a site?

Yes for the investigation. Status, events, logs, WordPress health and server services are all reads. Switching WP_DEBUG on, creating shell access and running a rescue need Full access and your explicit confirmation naming the site or server.

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