Claude Cowork + xCloud

Speed up a slow site with Claude Cowork on xCloud

Speeding up a slow site with Claude Cowork means handing the whole investigation to Anthropic's desktop agent, which reads your xCloud site and server data for one site or many and brings back a written diagnosis.

Skill: xcloud:performance
Toolsets: pagespeed, sites, servers, broken-links
Free with every xCloud account

Set up Claude Cowork All Claude Cowork guides

YouReview every site on the Frankfurt server for performance and rank them.

servers_monitoringread-only

sites_cacheSettingsread-only

sites_pagespeed_latestread-only

AgentSix sites checked. Server disk is at 88 percent, which slows the database for all of them. Two sites have no page cache and the weakest mobile results: shop.example.com and blog.example.com. Turning caching on is a dashboard step for each. The full ranking is below.

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 Claude Cowork to Speed up a slow site on xCloud?

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

1
Add xCloud as a custom connector
In Cowork, open Customize, then Connectors, and choose Add custom connector. If you already added xCloud to your Claude account, look for it in that list first. Name it xcloud, use this URL and sign in when the xCloud approval page opens.
URL
```
https://app.xcloud.host/mcp
```
2
Check the connection
Start a task and ask this first. Claude Cowork calls xCloud and names your account and the teams you approved, so you know the connector works before you delegate real work.
Prompt
```
Who am I on xCloud?
```
3
Match the access level to the job
Optional. On the xCloud approval screen, Full access lets a delegated job deploy, update plugins and renew certificates; Read-only is enough for audits and reports. To change the level later, reconnect the connector and approve again. A Team or Enterprise owner adds the same URL under Organization settings, then Connectors.
URL
```
https://app.xcloud.host/mcp
```

Check it worked

Then ask Claude Cowork for the job itself, for example:

Prompt

Review every site on my Frankfurt server for performance. For each one tell me whether page cache and object cache are on, what the latest mobile PageSpeed result is, and rank the sites from slowest to fastest.

In practice

How Does Performance Work from Claude Cowork?

Cowork is built for jobs you would otherwise do in a dashboard with a dozen tabs open, and a performance sweep is exactly that. Instead of asking about one domain, you can describe an outcome: look at every site on the Frankfurt server, find the ones with no page cache or an object cache that is off, compare their latest PageSpeed results and give me a ranked list. Cowork resolves the servers and sites, then repeats the same read chain on each, sites_cacheSettings, sites_pagespeed_latest and sites_monitoring_history, and reads servers_monitoring once for the shared machine, because a neighbour that eats the CPU can explain several slow sites at once.

What you get back is shaped like a document, not a stream of replies: a ranked list, the numbers behind each entry, and a short section on which fixes are dashboard switches that you have to flip yourself. A Read-only connection is enough for all of it, since the latest PageSpeed run, the cache layers, the services and the PHP version are all reads. It is also the safer choice when the task runs while you are away from the desk, because nothing in the sweep can then purge a cache or spend a scan.

The things to watch are the ones a long task creates. The access log is read over SSH and is slow, so ask for it on the two or three sites that look odd, not on every site. A site that errors instead of loading slowly is a different job, so tell Cowork to treat it as troubleshooting, which works from logs and events. And when the report names a cause such as a stopped Redis next to an object cache that reads as on, ask Cowork to quote the service status and the cache setting side by side, so you can see the evidence and not only the conclusion.

Claude Cowork specific: Choose the access level before the sweep starts. Read-only covers every read in the chain, and a Cowork task approved that way cannot purge a cache or start a PageSpeed scan on any site, however the prompt is worded. Full access lets it do both, and a sweep is the wrong place for purges on live sites, so ask Cowork to list where a scan or purge would help and run those one at a time. Changing the level means reconnecting the connector and approving again.

What xCloud does for performance

xCloud reads the site's and the server's CPU, RAM and disk samples, which cache layers are on, the latest PageSpeed result, traffic in the access log, service health and the site's PHP version. The agent names the cause from that data, then hands you the switches that only the dashboard can flip.

Resolve the site and its server. The agent looks up the site and the server it runs on, because the answer often comes from both. A slow site is frequently slow because a neighbour on the same server is.
Check status and monitoring history. A site that is mid-deploy or failed explains slowness without any measurement. Otherwise the agent reads the site's and the server's samples, and a 24-hour or 7-day series to tell whether the slowdown is new. Disk comes early: a nearly full disk slows everything, the database first.
Read the cache layers. The agent reads the cache settings before saying anything about caching: whether page cache, Redis or Object Cache Pro object cache and Cloudflare edge cache are on, and which server stack the site runs. It never reports that no cache configuration is readable without calling it.
Read PageSpeed and traffic. The latest completed PageSpeed run is free to read. A new scan is worth starting only when there is no result or the site changed since, and the agent tells you it is spending a scan. The access log shows spikes, a crawl or one client hammering a path.
Check services and PHP. The agent checks that PHP, the web server, Redis and the database are running, and reads the site's PHP version and pending updates. A stopped Redis next to an object cache that reads as on is a found answer.
Name the cause and hand off. You get the most likely cause with its numbers. The fix is either something the agent can do, such as a purge after you agree, or a dashboard switch it names with the path and the site's dashboard link. If every number looks normal, it says so instead of inventing a cause.

Reference

Performance Settings and Limits on xCloud

The facts Claude Cowork works within when it speeds up a slow site. Where a row names the dashboard, that step stays yours to take there.

Setting or limit	What applies
Monitoring history	Site and server CPU, RAM and disk samples as a 24-hour or 7-day series. History is not available on the free plan, and the agent says that is a plan limit rather than reporting no data
Cache state	Read through sites.cacheSettings: page cache, object cache (Redis, Object Cache Pro) and Cloudflare edge cache. It returns settings only, never cache contents
Enabling a cache layer	Dashboard-only: Site, WordPress, Caching. The API reads the layers and purges them, and cannot switch one on for an existing site
Page cache details	Cache duration, URL and cookie exclusions and ignored query parameters are dashboard-only and are not returned by the cache settings read
PageSpeed	The latest mobile and desktop results and the history are read for free. One scan runs both strategies
Scan conflicts	A 409 while a scan is running means it is still pending or scanning. The agent polls it instead of starting another, and it is not a cooldown
Cache purge	Purging runs without a confirmation stop but throws away a warm cache, so the agent asks first on a live site and reports each layer as queued or skipped
Traffic	The access log shows spikes and bots. It is read over SSH, so the agent asks for a bounded window
PHP version	Read from the site's status. Changing one site's PHP version is a dashboard step: Site, Site Settings
Server PHP default	Changing the server default PHP changes only the command-line php and the version new sites get. It does not move any existing site
Broken links	A broken-link scan on a WordPress site returns findings grouped by source page, and a truncated scan is reported as partial

Rules Claude Cowork has to follow

The agent diagnoses from measurements, not guesses, and it calls the cache settings read before it says anything about caching.
It never offers to turn on Redis or any other cache layer itself. Enabling a layer is a dashboard step, and the agent gives you the path and the dashboard link.
It never presents a change of server PHP default as a substitute for changing one site's PHP version.
A cache purge on a live site, a new PageSpeed scan and any server-level PHP change are announced first. Server-level changes also need your explicit yes.
A site that errors rather than loads slowly goes to troubleshooting, and a failed deploy goes to deploy.

Example prompts

What Can You Ask Claude Cowork to Do for Performance?

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

Review every site on my Frankfurt server for performance. For each one tell me whether page cache and object cache are on, what the latest mobile PageSpeed result is, and rank the sites from slowest to fastest.

Prompt

The Frankfurt server feels sluggish. Check its CPU, RAM and disk over the last seven days, then list which sites on it look responsible.

Prompt

Write me a one-page report on why shop.example.com is slow: what the data shows, the most likely cause, and which fixes I have to make in the xCloud dashboard.

Prompt

Why is shop.example.com slow? Check the cache, the server load and the latest PageSpeed result.

Prompt

Is Redis object cache on for the shop site? If it is off, tell me where to switch it on.

Prompt

Show CPU, RAM and disk for the shop site over the last 24 hours and tell me whether the slowdown is new.

Prompt

Run a PageSpeed scan on the shop site and compare the score with the previous scans.

Prompt

Look at the access log of the shop site for a traffic spike or a bot hammering one path.

Prompt

Which PHP version is the blog site running, and are there pending updates I should apply?

Prompt

Purge all caches on the shop site.

Prompt

Scan the shop site for broken links and list the pages with the most.

Claude Cowork and Performance: Frequently Asked Questions

What people ask before they let Claude Cowork speed up a slow site through xCloud.

Can Claude Cowork check performance across all my sites at once?

Yes. Describe the outcome and Cowork runs the same reads on each site, then reports one ranked list. It reads the shared server once, and it keeps the access log for the few sites that look odd, because that read is slow.

Why does my Cowork performance report say history is a plan limit?

Monitoring history is a paid-plan feature, so xCloud refuses the request on a free plan. Cowork should report that wording and carry on with the samples, cache settings and PageSpeed data that the plan does include. If every site shows a plan limit, check the team's plan before you trust the ranking.

Can the agent turn on caching for my slow site?

No. It can read which cache layers are on and purge them, but switching page cache, Redis object cache or Cloudflare edge cache on for an existing site is a dashboard step under Site, WordPress, Caching. The agent tells you the path and gives you the site's dashboard link.

What does a 409 mean when the agent starts a PageSpeed scan?

It means a scan for that site is still pending or running. The agent polls the existing scan instead of starting another, and it is not a cooldown period. A new scan is only worth starting when there is no recent result or the site has changed.

Will changing the server's PHP default speed up my site?

No. The server default changes only the command-line php and the version new sites get, and it does not move any existing site. The PHP version of one site is changed in the dashboard under Site, Site Settings.

Why does the agent say monitoring history is unavailable?

Monitoring history is a paid-plan feature, so on the free plan the request is refused as a plan limit. The agent reports it that way rather than saying there is no data, and it falls back to the samples and measurements the plan does include.

Does purging the cache ask for my confirmation?

xCloud itself runs a purge without a confirmation stop, because it is a routine action. The agent still asks you first on a live site, since a purge throws away a warm cache and the next visitors wait while it rebuilds.

Other agents