Antigravity + xCloud

Troubleshoot a broken site with Antigravity on xCloud

Troubleshooting with Antigravity means asking Google's agentic IDE why a site returns a 500 or a 502, and having its agent read xCloud's status, events and web server error log while you approve each tool in the panel.

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

Set up Antigravity All Antigravity guides

Youstaging.example.com returns 502 since the last deploy. Find the cause, no changes.

sites_statusread-only

sites_eventsread-only

AgentStatus is normal. The last deploy task finished with an error: npm run build exited 1 because DATABASE_URL is not set. I would read the error log to confirm.

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 Antigravity to Troubleshoot a broken site on xCloud?

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

1
Add xCloud in View raw config
In the Antigravity IDE, click the three dots at the top of the agent side panel, choose MCP Servers, then Manage MCP Servers, then View raw config. Paste this into mcp_config.json and save. The field is serverUrl: it is the only remote URL property in Antigravity's documented configuration, so do not write url or httpUrl.
JSON
```
{
  "mcpServers": {
    "xcloud": {
      "serverUrl": "https://app.xcloud.host/mcp"
    }
  }
}
```
2
Sign in, then check the connection
Open Agent settings (Cmd+, on Mac, Ctrl+, on Windows and Linux), go to Customizations and click Authenticate next to xcloud. Approve the teams and the access level in the browser, copy the authorization code it shows, paste it into the settings panel and click Submit. Then ask this in the agent panel.
Prompt
```
Who am I on xCloud?
```
3
No browser sign-in? Use an API key
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 add it as a header. Replace YOUR_TOKEN with the token, which contains a pipe character, and never paste it into chat. Keep this file out of git.
JSON
```
{
  "mcpServers": {
    "xcloud": {
      "serverUrl": "https://app.xcloud.host/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_TOKEN"
      }
    }
  }
}
```

Check it worked

Then ask Antigravity for the job itself, for example:

Prompt

staging.example.com returns 502 since the last deploy. Use xCloud to check status, recent events and the nginx error log, and quote the evidence.

In practice

How Does Troubleshooting Work from Antigravity?

In the Antigravity agent panel you describe the failure the way you would to a teammate: staging.example.com started returning 502 an hour ago, find out why but change nothing. Antigravity runs MCP tools you have not configured in Ask mode, so the first thing you notice is that it asks before each xCloud call. For an investigation that means a prompt for the status read, another for recent events, another for the nginx log and another for WordPress health. That is safe, and it is also the reason to set up your permissions before the incident rather than during it.

Antigravity's permission policy accepts patterns in the form mcp(server/tool). For this job you can allow the read tools by name, mcp(xcloud/sites_status), mcp(xcloud/sites_events), mcp(xcloud/sites_access-logs), mcp(xcloud/sites_wordpress_status) and mcp(xcloud/servers_services), so the evidence chain runs through without interruption. Everything else keeps its prompt. That includes WP_DEBUG, temporary shell access and the rescue action, which xCloud separately refuses without an explicit confirmation naming the site or server. A change therefore has to get past Antigravity's prompt and xCloud's stop.

What comes back is a plain account of the evidence in the order xCloud reads it. The agent says whether the site is in a normal state, which recent task failed, if any, and quotes the error log lines that support a cause. If the failing file is in the workspace, it can open it in the editor next to the log. If there is no evidenced cause, it lists what it ruled out and gives you the dashboard path, Site, Site Monitoring, Logs, for the WordPress debug.log. It will not restart PHP or reboot the server on a hunch, because that destroys the logs it was about to read.

Antigravity specific: Ask mode turns one investigation into a string of prompts, and the cure is a narrow allow list, not a wildcard. Allow the five read tools by their exact names with mcp(xcloud/tool_name). A pattern like mcp(xcloud/*) would also let sites_wp-debug and sites_rescue skip Antigravity's prompt, leaving xCloud's confirmation as the only stop. Also finish the OAuth step before you need it: the sign-in ends with an authorization code you paste into Settings, Customizations, and a half-finished sign-in means no xCloud tools at all.

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 Antigravity 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 Antigravity 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 Antigravity 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

staging.example.com returns 502 since the last deploy. Use xCloud to check status, recent events and the nginx error log, and quote the evidence.

Prompt

Which xCloud tasks failed on shop.example.com today? Show the output of the failed one.

Prompt

Check whether PHP and the database are running on the Frankfurt server. Read only, no restarts.

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.

Antigravity and Troubleshooting: Frequently Asked Questions

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

Why does Antigravity ask permission for every xCloud read?

Antigravity runs MCP tools you have not configured in Ask mode. Allow the read tools one by one with patterns such as mcp(xcloud/sites_status), and the investigation will run without a prompt for each read while changes still ask.

Does Antigravity use the nginx error log to find the cause?

Yes. The agent asks xCloud for the nginx log type with a limit, which returns the error log and the firewall logs, and it quotes the lines that support a cause. It cannot read the WordPress debug.log, which is in the dashboard under Site, Site Monitoring, Logs.

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