Cursor + xCloud

Troubleshoot a broken site with Cursor on xCloud

Troubleshooting a broken site with Cursor means asking the editor's agent why a site is failing, and letting it read xCloud's status, events and error logs while the project that produced the error is open beside it.

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

Set up Cursor All Cursor guides

Youshop.example.com is returning 500. Find the cause and open the file if it is in this project.

sites_statusread-only

sites_access-logsread-only

AgentStatus is normal. The error log shows a PHP fatal in app/Checkout.php line 88 at 14:02. I have opened that file next to the chat.

YouIs that line from my last commit?

AgentYes. The function it calls was renamed in that commit. The call at line 88 still uses the old name.

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 Cursor to Troubleshoot a broken site on xCloud?

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

1
Add xCloud to mcp.json with the compact URL
Cursor stops at 40 tools per server, and the full xCloud server advertises one tool per customer-facing operation, so start with the compact profile: five tools that still reach every operation. Put this in ~/.cursor/mcp.json for all projects, or .cursor/mcp.json inside one project.
JSON
```
{
  "mcpServers": {
    "xcloud": {
      "url": "https://app.xcloud.host/mcp?profile=compact"
    }
  }
}
```
2
Or add it from Cursor's MCP settings
Cursor's docs manage MCP servers from the Customize page. Add a new server there and paste the compact URL instead of editing the file. Use the plain https://app.xcloud.host/mcp URL only if your Cursor version loads every tool.
URL
```
https://app.xcloud.host/mcp?profile=compact
```
3
Sign in to xCloud
Cursor supports OAuth for remote servers and shows a login prompt next to xcloud. Click it, approve the teams and choose Read-only or Full access in the browser, then ask this to confirm.
Prompt
```
Who am I on xCloud?
```

Check it worked

Then ask Cursor for the job itself, for example:

Prompt

Why is shop.example.com returning 500? Check status, then events, then the nginx error log. If it names a file, open it here.

In practice

How Does Troubleshooting Work from Cursor?

You are in Cursor with the project open, a user has reported a 500, and you would rather not leave the editor to find out why. In the agent panel you ask what is wrong with shop.example.com. Cursor works through the xCloud connection, and because you connected with the compact URL it reaches operations through a small set of search and call tools rather than one tool per operation. It looks up the troubleshooting workflow, then runs the reads in order: the site status, the recent events, and the nginx log type of the access-logs operation with a limit. Each step comes back in the panel, with the log lines it is relying on quoted as data.

The editor context is what Cursor adds. A PHP fatal in the error log names a path such as app/Checkout.php and a line number, and Cursor can open that file in the same window, show you the lines around it and compare them with your most recent changes. For a site deployed from Git, that closes the loop between the server's evidence and the code that produced it, and a fix is an edit in the editor you already have open. For a fault that is not in the code, such as a stopped database service or a failed task, Cursor reports what each check showed and does not restart anything to see whether the error goes away.

Changes on the xCloud side still wait for you. Turning WP_DEBUG on, creating temporary shell access and running a rescue each need a yes that names the site or server, and Cursor turns WP_DEBUG back off and asks to remove the shell user when it finishes. If the logs you can read through xCloud do not explain the fault, it tells you which logs are dashboard-only and where to find them, rather than guessing.

Cursor specific: Cursor stops at 40 tools per server, so connect with the compact URL, https://app.xcloud.host/mcp?profile=compact, or the troubleshooting tools will not all load. The read chain is slow in one place, the error log, because xCloud reads it over SSH, so ask for a bounded window. A project-level .cursor/mcp.json travels with the repository, which is fine for the URL but a reason to keep any API token out of it. If you opened a different folder than the one deployed to the site, the file named in the log will not be there to open.

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 Cursor 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 Cursor 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 Cursor 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

Why is shop.example.com returning 500? Check status, then events, then the nginx error log. If it names a file, open it here.

Prompt

Read the nginx error log for the last hour and tell me whether the failing line is in this workspace or on the server.

Prompt

Did any task on blog.example.com fail before it broke? Do not change anything, and ask before turning on WP_DEBUG.

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.

Cursor and Troubleshooting: Frequently Asked Questions

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

Does Cursor need the full xCloud tool list to troubleshoot a site?

No. The compact profile exposes five tools that still reach every operation, including the status, events and log reads this job uses. It also keeps the connection under Cursor's 40-tool cap, which the full server would exceed.

Can Cursor open the file named in the xCloud error log?

Yes, when that path exists in the folder you have open. Cursor reads the log through xCloud, opens the file locally and explains the fault. If the fault is not in the code, it reports what the checks showed instead.

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