Warm the WordPress cache with OpenClaw

Warming the WordPress cache with OpenClaw means giving an always-on agent a standing job: start the xSpeed preloader through xSpeed Hub on a schedule, check how far each crawl got and tell you the result.

list_sitesget_cache_statusget_settingsupdate_settingsstart_preloaderget_preloader_statusstop_preloader

Last updated: October 2026

Example session · OpenClaw

You: Set up a nightly warm for shop with xSpeed Hub. Start the crawl, check it later, report in the morning.

OpenClaw: I saved the routine. It calls start_preloader for shop each night and get_preloader_status an hour after. Running it once now to test.

start_preloader(site: shop) changes site
→ Queued 230 URLs from the sitemap; pages are fetched in the background

get_preloader_status(site: shop) read-only
→ Running, 20 of 230 URLs warmed

OpenClaw: The test run works: the crawl is going. Tonight's run will report the final count.

How OpenClaw handles this

Most clients wait for you to type. OpenClaw keeps running and has its own scheduled automations, which makes it the one agent here that can warm a cache while you are asleep. You describe the routine once and OpenClaw saves it as two automations: one starts the preloader on each site every night after the backups, and one an hour later reads the progress and messages you the sites that did not finish. The first calls start_preloader, the second get_preloader_status.

The Hub does not schedule anything for agents. It runs its own daily checks and sends alerts, but it has no timer that triggers a prompt, so the clock is OpenClaw's. The plugin has a schedule of its own too: the Crawl Now settings offer a crawl that repeats hourly, daily or weekly, described in /docs/crawl-now/. A good setup uses that for baseline coverage and uses OpenClaw for the times that matter, such as right after a purge.

Unattended writes need a decision from you before you save the routine. An isolated automation run has nobody to approve a tool call, so the Hub's instruction to confirm once before a call across every site has nobody to answer it, and the Hub has no confirmation step of its own. Two OpenClaw settings decide what the job can do. The tools list on the automation names the only tools the run may call, such as xspeedhub__get_preloader_status, and a per-server tool filter leaves tools out for every agent. When the Codex runtime runs your turns, the default full-permission posture does not prompt, so do not count on an approval to stop a start. A quiet week of reports with every site marked done is the result to aim for, and the first failed report tells you which site to look at.

Set up OpenClaw once

Already connected? Skip to the prompts. Alternatives and troubleshooting are on the OpenClaw 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.

2Save xSpeed Hub as an MCP server

Run this on the machine that hosts your OpenClaw Gateway. Set the transport to streamable-http: OpenClaw falls back to SSE when you leave it out. With --auth oauth the command saves the server without a connection test, because sign-in has to happen first.

Terminal

openclaw mcp add xspeedhub \
  --url https://app.xspeedcache.com/xspeed/mcp \
  --transport streamable-http \
  --auth oauth

3Sign in with openclaw mcp login

OpenClaw prints an authorization URL and listens on a loopback address for the callback. Open the URL, sign in to xSpeed Hub and approve; the token exchange finishes by itself. There is no token to paste. If your browser is on another machine, copy the code from the redirect and pass it back with openclaw mcp login xspeedhub --code. Then check the connection.

Terminal

openclaw mcp login xspeedhub
openclaw mcp doctor xspeedhub --probe

1 / 3

Full OpenClaw 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. OpenClaw gives you two client-side gates, and the Hub adds none. First, openclaw mcp tools xspeedhub --include limits which tools exist for the agent, so a list of read tools keeps every write out of reach. Second, when the Codex runtime runs your agent turns, MCP tool approvals follow the session's permission posture, and the default full-permission posture does not prompt. openclaw mcp configure xspeedhub --approval prompt asks on every call, and Allow Always saves a grant for that one tool with any arguments. OpenClaw's docs describe that per-call prompt for the Codex runtime; with its own embedded runtime, use the tool filter to decide what the agent can call. The Hub has no confirmation step of its own.

What do I ask?

Three prompts written for OpenClaw. More for this job are below.

Prompt for OpenClaw

Every night at two, use xSpeed Hub to start the preloader on shop and blog, then check progress at three and message me the result.

Prompt for OpenClaw

Set up a morning check that asks xSpeed Hub for the preloader status on every site and lists the ones that are idle.

Prompt for OpenClaw

Use xSpeed Hub to run a warm-up on docs now, and again an hour after each purge you see.

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.

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.

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.

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.

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.

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.

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.

Reference

Start and stop	start_preloader and stop_preloader (write)
Progress	get_preloader_status (read): running or not, processed out of total, last URL, recent errors
What gets crawled	The sitemap (the WordPress one at /wp-sitemap.xml unless you set another), nested indexes followed, excluded URLs skipped
Needs	The preloader module switched on (it is off by default) and page caching on
Pages per run	5 by default, 1 to 50, set in the preloader module
Schedule setting	manual, hourly, daily or weekly, set in the preloader module
Every site at once	start_preloader and stop_preloader accept site: "all"; get_preloader_status does not
Fan-out pacing	Sites start one after another with a 1 second pause, one result per site
Warmer user-agent	xSpeed-Warmer/1.0, the string a firewall rule would need to allow
Stopping	Safe mid-run; warmed pages stay cached
Read-only access	A 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.
Confirmation	None on the Hub; your client's prompt is the gate

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 OpenClaw

A scheduled job that writes runs with nobody watching, so there is no prompt for you to answer. If it only needs to report, give the automation a tools list with xspeedhub__list_sites and xspeedhub__get_preloader_status, or use the connection token with Read-only everywhere on (or a Viewer sign-in). If it must start crawls, name the start tool in that list, keep it to named sites rather than site: "all", and decide how it behaves if a site refuses because the preloader module is off.

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?

Frequently asked questions

Yes, because OpenClaw runs scheduled automations of its own. It calls start_preloader on each site at the time you choose. The Hub has no scheduler for agent prompts, so the timer is OpenClaw's, not the Hub's.

The plugin schedule gives steady baseline warming with no agent involved. Use an OpenClaw routine when you want a start tied to an event, such as after a purge, or a report on how each crawl went.

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.

Warm the cache, from OpenClaw.

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

Open xSpeed Hub OpenClaw setup

Warm the WordPress cache with OpenClaw

How OpenClaw handles this

Set up OpenClaw once

What do I ask?

What happens, step by step

Reference

Rules worth keeping

More prompts for this job

Frequently asked questions

Keep going

Warm the cache, from OpenClaw.