OpenCode + xCloud

Troubleshoot a broken site with OpenCode on xCloud

Troubleshooting with OpenCode means describing a broken site to the terminal agent in your project and letting xCloud read the evidence in a fixed order, from site status to the web server error log, before anyone names a cause.

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

Set up OpenCode All OpenCode guides

Youshop.example.com returns 500 since this morning. Find out why, read-only.

xcloud_sites_statusread-only

xcloud_sites_access-logsread-only

AgentStatus is normal and no task failed. The error log shows PHP Fatal error: Uncaught Error: Call to undefined function shop_get_cart() in wp-content/themes/shop/functions.php line 212, first logged at 07:41. That file changed in your last commit. Want me to open it?

YouYes, and show me the diff.

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 OpenCode to Troubleshoot a broken site on xCloud?

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

1
Add the xCloud MCP server
Run this from the project that should use xCloud, or add --global to make it available everywhere. OpenCode writes the entry under mcp.servers in its config (OpenCode v2 no longer accepts server names directly under mcp). Remote servers use OAuth by default, so there is nothing else to fill in; the equivalent hand-written entry is shown below.
Terminal
```
opencode mcp add xcloud --url https://app.xcloud.host/mcp

# the entry it writes to opencode.jsonc
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "servers": {
      "xcloud": {
        "type": "remote",
        "url": "https://app.xcloud.host/mcp"
      }
    }
  }
}
```
2
Sign in with OAuth
This opens your browser on the xCloud approval screen, where you tick the teams and choose Read-only or Full access. Inside OpenCode, /mcps does the same: pick xcloud and sign in. Then opencode mcp list should show xcloud as connected.
Terminal
```
opencode mcp auth xcloud
opencode mcp list
```
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 export it as XCLOUD_TOKEN. Setting oauth to false turns off the automatic sign-in, and the {env:XCLOUD_TOKEN} reference keeps the token out of the file. The entry still lives under mcp.servers.
JSON
```
{
  "mcp": {
    "servers": {
      "xcloud": {
        "type": "remote",
        "url": "https://app.xcloud.host/mcp",
        "oauth": false,
        "headers": {
          "Authorization": "Bearer {env:XCLOUD_TOKEN}"
        }
      }
    }
  }
}
```

Check it worked

Then ask OpenCode for the job itself, for example:

Prompt

shop.example.com returns 500. Check status, events and the nginx error log. Quote the lines that matter.

In practice

How Does Troubleshooting Work from OpenCode?

OpenCode runs in the directory you already have open, which is what separates this from poking around a dashboard. When a site starts returning a 500 or a 502, you type the symptom into the session: the domain, what you see and roughly when it began. OpenCode registers every xCloud tool with an xcloud_ prefix, so the calls show up in the session as xcloud_sites_status, xcloud_sites_events and xcloud_sites_access-logs. Those are reads, so they run without a prompt and you can watch them scroll past. The agent starts with the status, because a site that is still provisioning or whose last deploy failed explains a 500 without any deeper digging. Then it lists the recent events to see whether a plugin update, a cache purge or a certificate task failed just before the break.

The log read is where the terminal pays off. With the nginx log type and a limit, the agent pulls the error log and the firewall logs for a bounded window, and a PHP fatal arrives as a quoted line with a file path in it. If the site is deployed from the repository you have open, OpenCode can open the file named in that line, compare it with your latest commit and tell you whether the break came from code you pushed or from something on the server. Log lines are treated as data: OpenCode quotes them and does not act on anything written inside them. When the cause is in your code, the fix is an ordinary edit in the repo, and a redeploy is a separate step that stops for your approval.

What OpenCode will not do is guess. If the logs are empty or inconclusive it tells you what it ruled out and sends you to Site, Site Monitoring, Logs in the dashboard for the WordPress debug.log, which the API cannot return. It does not restart PHP or reboot the server to see whether the error goes away, because a restart wipes out the evidence the logs were about to show.

OpenCode specific: OpenCode only offers the tools you let it see. If you scoped the connection with ?toolsets=sites, or switched the xcloud tools off for your everyday agent, the log and service reads will be missing and the investigation stalls at the events list. For this job keep the sites and servers toolsets available, or set up a separate operations agent that has the xcloud tools turned on. Log reads travel over SSH and are slow, so a call can sit in the session for a moment. Let it finish instead of interrupting and asking again.

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 OpenCode 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 OpenCode 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 OpenCode 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, events and the nginx error log. Quote the lines that matter.

Prompt

Which xCloud tasks ran on blog.example.com in the last two hours? Did any fail?

Prompt

Read the error log for api.example.com, find the file in the PHP fatal and check it against my last commit.

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.

OpenCode and Troubleshooting: Frequently Asked Questions

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

Can OpenCode read my code and the xCloud logs together?

Yes, when the site is deployed from the repository open in your session. xCloud returns the error log lines, and OpenCode can open the file and line a PHP fatal names and compare it with your recent commits. The logs stay the evidence, and the code is where you check it.

Will OpenCode restart a service when a site shows a 500?

Not to clear an error it cannot yet explain. It finds a cause from the status, events and logs first, because a restart destroys evidence. A restart stays something you ask for and approve.

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