Hermes Agent + xCloud

Troubleshoot a broken site with Hermes Agent on xCloud

Troubleshooting with Hermes Agent means messaging an always-on agent from Telegram, Slack or the terminal when a site breaks, and having it walk xCloud's evidence in order and report back in the same chat.

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

Set up Hermes Agent All Hermes Agent guides

Youapi.example.com is giving 502s. What is going on?

sites_statusread-only

sites_access-logsread-only

AgentStatus is normal. The error log shows upstream prematurely closed connection while reading response header from upstream, repeated since 06:12, and no failed task before it. That points at the PHP process, but the log does not say why. Want me to check the server services?

YouYes.

servers_servicesread-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 Hermes Agent to Troubleshoot a broken site on xCloud?

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

1
Add the xCloud MCP server
Add this under mcp_servers in ~/.hermes/config.yaml. If the file already has an mcp_servers block, add only the xcloud entry. Then start a new Hermes session, or run /reload-mcp in the one that is open.
YAML
```
mcp_servers:
  xcloud:
    url: "https://app.xcloud.host/mcp"
    auth: oauth
```
2
Authorize xCloud
On first connect Hermes prints an authorize URL and waits for the sign-in. Run this command to start it yourself or to re-authorize later. On the xCloud approval screen tick the teams and choose Read-only or Full access. Hermes caches the tokens in ~/.hermes/mcp-tokens/xcloud.json and reuses them on later runs.
Terminal
```
hermes mcp login xcloud
```
3
No browser? Use an API key
For a server with no browser, 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 send it as a header in place of auth: oauth. Keep ~/.hermes/config.yaml out of version control when it holds a token.
YAML
```
mcp_servers:
  xcloud:
    url: "https://app.xcloud.host/mcp"
    headers:
      Authorization: "Bearer YOUR_TOKEN"
```

Check it worked

Then ask Hermes Agent for the job itself, for example:

Prompt

shop.example.com is showing a critical error. Check it on xCloud and tell me what the logs say, in three lines.

In practice

How Does Troubleshooting Work from Hermes Agent?

Hermes Agent is not a window you open once a site is already on fire. It runs as a gateway on a machine you keep on, and you reach it from Telegram, Discord, Slack, WhatsApp or Signal, so the first report of trouble often comes from your phone: shop.example.com is giving me a 500. Hermes answers in the same thread. It calls sites_status first and then sites_events, and it sends back short lines that read well on a small screen: the site is in a normal state, a plugin update task finished with an error just before the break, here is that task's output. Reads need no approval, so nothing waits on you until the agent wants to change something.

Memory is the difference you notice over weeks. Hermes keeps what you told it, so you can say once that shop is the WooCommerce site on the Frankfurt server and the blog is the one with a staging copy, and later reports can shrink to the shop is down. Treat that memory as a way to find the right site, never as evidence. The cause still has to come from a log line or an event fetched during this investigation, so Hermes reads the nginx error log again with a limit each time, even when the last outage looked identical. When the evidence runs out, it sends the dashboard path, Site, Site Monitoring, Logs, and the site link xCloud returned, so you can open the WordPress debug.log in your phone's browser.

Because Hermes has a built-in scheduler, you can also hand off the first look. A cron job that runs in a fresh session can check every site's status and recent events every hour and message you only when one is not in a normal state, with the failing event attached. Scheduled runs are for reading. Turning on WP_DEBUG, creating temporary shell access and running a rescue each need a yes naming the site, and a job with nobody present cannot give one, so those steps wait for a message from you.

Hermes Agent specific: Hermes reads mcp_servers when a session starts, and a gateway that has been running for days keeps the tool list it started with. If you edit config.yaml or re-authorize with hermes mcp login xcloud, run /reload-mcp or restart the gateway, or the moment of an outage is when you find the xCloud tools missing. A scheduled watch reuses the cached sign-in, so if it lapses, run hermes mcp login xcloud again and check that the job still reports.

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 Hermes Agent 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 Hermes Agent 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 Hermes Agent 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 is showing a critical error. Check it on xCloud and tell me what the logs say, in three lines.

Prompt

Every hour, check the status and recent events of all my sites. Message me only if one is not in a normal state, and change nothing.

Prompt

Last week blog.example.com broke after a plugin update. Check whether the same thing happened today, but read the logs again before you say so.

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.

Hermes Agent and Troubleshooting: Frequently Asked Questions

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

Can Hermes Agent tell me when a site goes down without me asking?

Yes, through its built-in cron scheduler. A job can read site status and recent events on a timer in a fresh session and message you in a chat only when something is not normal. Keep the job to reads, because changes still need your approval.

Does Hermes Agent remember the cause of an earlier outage?

It remembers what you told it, which helps it find the right site and server quickly. It does not treat that as proof, so it reads the status, events and error log again for each new incident before it names a cause.

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