xSpeed Cache is officially live! Get 50% OFF during Launch Week — Lifetime starts at just $79Lifetime from $79 — 50% OFF, Launch Week! See Plans →

See Plans →
Features
xSpeed Hub Pricing Docs Blog Scan
Appearance
Get Plugin

Warm the WordPress cache with Claude Cowork

Warming the WordPress cache with Claude Cowork means handing the desktop agent a whole warm-up task, such as every launch site, and letting it start and follow the xSpeed preloader through xSpeed Hub.

list_sitesget_cache_statusget_settingsupdate_settingsstart_preloaderget_preloader_statusstop_preloader

Last updated: October 2026

Example session · Claude Cowork

You: The launch sites just went live. Use xSpeed Hub to warm shop, blog and docs and report back.

list_sites read-only
→ 3 sites in this workspace: shop, blog, docs

Claude Cowork: I will call start_preloader on shop, blog and docs together, one site after another. That touches all 3 sites. Go ahead?

You: Yes.

start_preloader(site: all) changes site
→ 3 sites: shop and blog started, docs refused because its preloader module is off

Claude Cowork: Two crawls are running. docs refused to start: its preloader module is off, so nothing is warming there. I can read its settings if you want to turn it on.

01

How Claude Cowork handles this

Cowork is built for tasks with several steps, and a launch day is one. You write what you want finished: warm the three sites that just went live, check that each crawl started, and tell me which ones need attention. Cowork works through that on your desktop, using the xSpeed connector that is already on your Claude account. It lists your sites, calls start_preloader for each one, and then reads get_preloader_status to see where each crawl stands.

What you get back is a short report per site rather than raw tool output: started, running with a count of pages warmed, or refused with the reason. A site refuses when its preloader module is switched off, and a good report says so by name. If one crawl is hurting a site that is busy, ask Cowork to stop that one with stop_preloader. Pages already warmed stay in the cache, so the stop is safe at any point.

Cowork has three approval modes, and they are separate from xSpeed Hub. In Manual mode a tool set to Needs approval waits for your Allow or Deny, and one set to Always allow runs. Auto keeps working and blocks what Claude judges unsafe, and Skip asks nothing. Each Hub tool gets its setting under Customize > Connectors: Always allow, Needs approval or Blocked. The Hub has no confirmation step, so under Skip, or for a tool set to Always allow, a start runs as soon as your connection allows writes. Read the plan Cowork proposes before it begins, especially when the plan says it will start the preloader on more than one site.

02

Set up Claude Cowork once

Already connected? Skip to the prompts. Alternatives and troubleshooting are on the Claude Cowork guide.

1Put your sites in xSpeed Hub

Sign in at app.xspeedcache.com with Google or email; the Hub is free and has no site cap. Then connect each WordPress site from its own dashboard: click Connect Hub in the xSpeed Cache top bar, then Connect via xSpeed Hub. Each site needs the free xSpeed Cache plugin.

2Add xSpeed Hub to your Claude account

Cowork does not keep its own connector list. In Claude, go to Customize > Connectors, click Add custom connector, name it xspeedhub, paste the URL, choose Sign in now and, if asked, Register automatically. The full steps, including the Team and Enterprise route, are on the Claude page: /agent/claude/.

Text
https://app.xspeedcache.com/xspeed/mcp

3Connect, then start a new Cowork session

Click Connect on the connector and approve access on the xSpeed Hub page. Cowork loads the connectors enabled for your account when a session starts, so open a new Cowork session after you connect. You can also switch the connector on from the + menu in the chat box.

Text
Customize  >  Connectors  >  xspeedhub  >  Connect

4Set tool permissions before the first task

Open the connector under Customize > Connectors and set each tool to Always allow, Needs approval or Blocked. A sensible start is Always allow for the read tools and Needs approval for purge_cache, toggle_cache, update_settings and the other writes. Then pick a Cowork mode; Manual is the one that shows you each request.

Text
Tool permissions: get_cache_status = Always allow
Tool permissions: purge_cache = Needs approval
1 / 4

Full Claude Cowork setup, sign-in options and FAQ

Before you send a prompt that changes something

Reads change nothing on your sites, though contact_support emails xSpeed support. Writes run once your connection allows them, so your client's approval prompt and a read-only connection (the token's Read-only everywhere switch, or a Viewer sign-in) are the gates that matter. Cowork has three modes. Manually approve (Manual) pauses and asks you to Allow or Deny each action. Automatically approve (Auto) keeps working and blocks what Claude judges to be unsafe. Skip all approvals (Skip) asks nothing and checks nothing. Each connector tool also has a permission, set under Customize > Connectors. In Manual mode, Always allow runs, Needs approval asks and Blocked is denied; in Skip mode only Blocked stops a call. xSpeed Hub has no confirmation step of its own, so under Skip, or for any tool set to Always allow, a write runs as soon as your connection allows writes. Auto relies on Claude's own judgement, which is not a lock.

03

What do I ask?

Three prompts written for Claude Cowork. More for this job are below.

Prompt for Claude Cowork
Use xSpeed Hub to warm the cache on shop, blog and docs, one after another, and report which crawls started.
Prompt for Claude Cowork
With xSpeed Hub, check the preloader on every site in my workspace and write me a one-line status for each.
Prompt for Claude Cowork
Use xSpeed Hub to stop the preloader on shop, then start it again on blog only.
04

What happens, step by step

The first visitor to an uncached page pays for building it. The preloader fixes that by visiting your pages first. Through xSpeed Hub an agent can start the crawl on one site or on every site in a workspace, watch how far it has got, and stop it. The crawl runs inside WordPress in the background; the agent only starts it, reads its progress and stops it.

01

Check the cache and the preloader

get_cache_status tells the agent whether page caching is on, because there is nothing to fill when it is off. get_preloader_status shows whether a crawl is already running, so the agent does not start a second one.

02

Make sure the preloader is switched on

The preloader module is off on a fresh install, and the site refuses start_preloader until it is on. The agent can read the module with get_settings and, if you agree, switch it on with update_settings on the preloader module. The Hub tells the agent to briefly confirm intent before an update_settings call, but that is guidance to the agent, not a lock.

03

Start the crawl

start_preloader makes the site read its sitemap, follow any nested sitemap indexes, drop URLs that your cache exclusion rules skip, and queue the rest. The call returns once the queue is built; the pages are then fetched in the background, a few per run. For every site at once the agent passes site: "all", and the Hub starts the sites one after another with a one-second pause.

04

Watch the progress

get_preloader_status reports whether a crawl is running, how many URLs it has processed out of the total, the last URL it visited and the most recent errors. It works on one site at a time, so for several sites the agent calls it once per site.

05

Read what failed

A page that answers 403 or 406 usually means a server firewall is blocking the warmer by its user-agent, not that the page is broken. The status message names the user-agent to allow. A crawl that queues no URLs is reported as an error with the reason, not as a success.

06

Stop it if the server struggles

stop_preloader ends a running crawl. It is safe mid-run: pages already warmed stay cached. The agent can stop one site or every site in the workspace.

05

Reference

Start and stopstart_preloader and stop_preloader (write)
Progressget_preloader_status (read): running or not, processed out of total, last URL, recent errors
What gets crawledThe sitemap (the WordPress one at /wp-sitemap.xml unless you set another), nested indexes followed, excluded URLs skipped
NeedsThe preloader module switched on (it is off by default) and page caching on
Pages per run5 by default, 1 to 50, set in the preloader module
Schedule settingmanual, hourly, daily or weekly, set in the preloader module
Every site at oncestart_preloader and stop_preloader accept site: "all"; get_preloader_status does not
Fan-out pacingSites start one after another with a 1 second pause, one result per site
Warmer user-agentxSpeed-Warmer/1.0, the string a firewall rule would need to allow
StoppingSafe mid-run; warmed pages stay cached
Read-only accessA Viewer member's sign-in, or the connection token with Read-only everywhere on: start_preloader and stop_preloader are refused; get_preloader_status works. An OAuth sign-in by anyone else gets the scopes the client asks for.
ConfirmationNone on the Hub; your client's prompt is the gate
06

Rules worth keeping

  • Warm after a purge, not instead of one. The Hub tells the agent that starting the preloader after a purge saves the next visitor from paying for the rebuild.
  • A crawl requests every page in the sitemap, so it adds load to the origin. Start with one site, and on a small host keep Pages per run low or stop the crawl if the site slows.
  • start_preloader and stop_preloader are write tools. The Hub calls the preloader low-risk and only asks the agent to confirm when the target site is unclear or the call covers every site, so your client's approval prompt and read-only access (a Viewer sign-in, or the connection token with Read-only everywhere on) are the gates that matter.
  • A fan-out only starts the crawls. Check each site with get_preloader_status afterwards, and treat some sites failing to start as a partial result, not a failure of the whole call.

Good to know with Claude Cowork

Cowork can only use the xSpeed connector if it is already added to your Claude account, and it syncs connectors when a session starts, so add the connector in Claude first and then open a new Cowork session. If a task says it has no xSpeed tools, that is almost always why. Keep start_preloader and stop_preloader on Needs approval and run a task that fans out over several sites in Manual mode. Skip asks nothing and checks nothing, and Auto leaves the decision to Claude's own judgement, which is not a lock. Blocked tools are denied in every mode.

07

More prompts for this job

They work in any client connected to xSpeed Hub.

Prompt
Use xSpeed Hub to start the preloader on shop and tell me how many URLs it queued.
Prompt
Using xSpeed Hub, how far through its crawl is blog? Show processed against total and any errors.
Prompt
With xSpeed Hub, purge the cache on docs, then warm it again.
Prompt
Use xSpeed Hub to start the preloader on every site in my workspace and tell me which ones refused.
Prompt
Use xSpeed Hub to stop the preloader on shop. It is slowing the server down.
Prompt
The preloader on shop says it is disabled. Use xSpeed Hub to turn the module on, then start the crawl.
Prompt
Using xSpeed Hub, which of my sites has no running crawl and a low hit ratio?
08

Frequently asked questions

Yes. It can call start_preloader with every site in a workspace, or a list of site handles, and the Hub returns a result per site. Sites run one after another with a one-second pause, and a refusal on one site does not stop the rest.

Cowork uses the connectors on your Claude account, so add xSpeed there first, following the Claude Cowork setup guide on this site. Once the connector is on the account, new Cowork tasks can call the xSpeed tools.

The preloader module is off by default on a new install, and the site refuses to start a crawl until it is on. The agent can switch it on with update_settings on the preloader module, or you can turn it on in the xSpeed Cache panel in wp-admin. Page caching also has to be on, because the crawl exists to fill that cache.

It reads the site's sitemap, which is the WordPress one at /wp-sitemap.xml unless you set a different sitemap URL, follows nested sitemap indexes and skips any URL your cache exclusion rules leave out. If the sitemap cannot be read, the site falls back to a list built from its own content and says so. If nothing at all is queued, the call reports an error with the reason.

Yes. The agent passes site: "all" to start_preloader and the Hub starts the crawl on every site in the workspace one after another, returning a result per site. The Hub tells the agent to confirm that with you once first. The call only starts the crawls, so progress is read afterwards with get_preloader_status, one site at a time.

A crawl fetches your own pages, a few per run, so it adds load while it runs. The Pages per run setting controls how many, from 1 to 50 with a default of 5. If a site struggles, stop_preloader ends the crawl and the pages already warmed stay cached.

Those codes are what bad-bot firewall rules usually answer with, and they mean the warmer was judged by its user-agent, not that the page is missing. The warmer identifies itself as xSpeed-Warmer/1.0. Allow that user-agent in the server rule, or change it with the xspeed_preloader_user_agent filter, and run the crawl again.

The preloader has its own Schedule setting in WordPress: manual, hourly, daily or weekly. An agent can change it with update_settings. The Hub itself has no scheduler for agent prompts, so a prompt only runs when you send it or when your AI client runs it on a timer.

09

Keep going

Warm the cache with other agents

More with Claude Cowork

Documentation

From the blog

Warm the cache, from Claude Cowork.

xSpeed Hub is free and has no site cap. Connect your sites once and ask from the agent you already use.