# Warm the WordPress cache with Grok

> Warming the WordPress cache with Grok means asking xAI's assistant on grok.com to start the xSpeed preloader on one of your sites through the xSpeed Hub connector, then asking it how far the crawl has got.

Page: https://xspeedcache.com/agent/grok/preload-cache/
Last updated: October 2026

You just purged a site, or a launch emptied the cache, and grok.com is the tab you have open. You type which site to warm. Grok calls start_preloader through the connector, and the plugin on that site reads its sitemap and queues the URLs. The call returns as soon as the queue is built, and the pages are then fetched in the background a few per run, so the answer in the chat is a count of queued URLs, not a finished crawl.

A while later you ask in the same chat how it is going, and Grok calls get_preloader_status: running or not, how many of the URLs are processed, the last one visited and any recent errors. A page answering 403 or 406 usually means a server firewall is blocking the warmer by its user-agent, and the status message names the user-agent to allow, so Grok can tell you what to change. If the start is refused because the preloader module is off, Grok can read the module and switch it on with update_settings once you agree. stop_preloader ends a crawl that is slowing the site, and warmed pages stay cached.

xAI's connector documentation describes no per-tool approval setting, and says Grok can use a connector's tools whenever your question relates to that service. xSpeed Hub has no confirmation step of its own, so a start runs once Grok calls it and your connection allows writes. The Hub calls the preloader low-risk and only asks the agent to confirm when the site is unclear or the call covers every site, so for a single named site Grok may simply start it. Say ask me first in the request if you want a question before any write, and read Grok's plan before you answer.

## Set up Grok once

### 1. Put 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.

### 2. Add xSpeed Hub as a custom connector

Go to grok.com/connectors, click New Connector and select Custom. Enter this as the MCP server URL and complete the authentication: approve access on the xSpeed Hub page that opens. Grok then reads the Hub's tools and makes them available in your conversations.

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

### 3. Ask a first question

Start a chat and ask something that names xSpeed Hub, so Grok reaches for the connector. A list of your sites with their cache status means the connection works.

```
Use xSpeed Hub to list my sites and tell me which ones have page caching turned off.
```

Full setup: https://xspeedcache.com/agent/grok/

### 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. xAI's connector documentation describes no per-tool approval setting. It says Grok can use a connector's tools whenever your questions relate to that service. xSpeed Hub has no confirmation step of its own, so a purge or a settings change runs as soon as Grok calls it and your connection allows writes. The Hub tells the agent to confirm the target site and to ask once before a write that touches every site, but that is an instruction, not a lock. If you want Grok to read and never change anything, sign in as a Viewer member of the workspace, which only ever gets read access. Otherwise read what Grok says it is about to do before you answer yes.

## Prompts

- Use xSpeed Hub to start the preloader on shop and tell me how many URLs it queued.
- Using xSpeed Hub, how far through its crawl is blog? Show processed against total and any errors.
- With xSpeed Hub, check whether the preloader module is on for docs. Ask me before you switch it on or start anything.

## Example session

```
You: Use xSpeed Hub to warm docs. I purged it after the guide update.
  → start_preloader(site: docs) [changes site]: Refused: the preloader module is disabled on this site
  → get_settings(site: docs, module: preloader) [read-only]: enabled false, pages per run 5, schedule manual
Agent: The preloader module is off on docs, which is the default on a new install, so the site refused the crawl. Switching it on changes the settings on docs. Turn it on and start the crawl?
You: Yes, turn it on.
  → update_settings(site: docs, module: preloader, values: { enabled: true }) [changes site]: Preloader module enabled
  → start_preloader(site: docs) [changes site]: Queued 152 URLs from the sitemap; pages are fetched in the background
Agent: The module is on and 152 URLs are queued. Ask me in a few minutes and I will read the progress.
```

## How it works

1. **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.
2. **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.
3. **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.
4. **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.
5. **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.
6. **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

- 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 Grok

xAI's connector documentation describes no scheduled connector runs, so Grok warms when you ask. For routine warming, use the plugin's own Schedule setting in the preloader module, which runs hourly, daily or weekly inside WordPress with no agent involved, and which Grok can change with update_settings if you ask. For chats that should only watch a crawl, sign in to xSpeed Hub as a Viewer member: the Hub refuses start_preloader and stop_preloader for that sign-in, and get_preloader_status keeps working. The connection token's Read-only everywhere switch does not apply, because the connector signs in with OAuth and xAI describes no header field for it. On Grok Business and Enterprise a team admin provisions the connector first.

## More prompts for this job

They work in any client connected to xSpeed Hub.

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

## Frequently asked questions

### Can Grok warm my WordPress cache?

Yes. With xSpeed Hub added as a custom connector on grok.com, ask Grok to warm a named site. It calls start_preloader, reports how many URLs were queued, and reads get_preloader_status when you ask for progress.

### Can Grok keep my cache warm on a schedule?

xAI's connector documentation describes no scheduled connector runs, so Grok warms when you ask. The preloader module has its own Schedule setting in WordPress, manual, hourly, daily or weekly, and Grok can change it with update_settings.

### Why does start_preloader say the preloader is disabled?

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.

### What does the preloader actually warm?

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.

### Can I warm every site with one prompt?

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.

### Will warming slow my site down?

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.

### Why do some pages fail with HTTP 403 or 406?

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.

### Can the agent keep my cache warm on a schedule?

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 with other agents

[Claude Code](https://xspeedcache.com/agent/claude-code/preload-cache/) · [Claude](https://xspeedcache.com/agent/claude/preload-cache/) · [Claude Cowork](https://xspeedcache.com/agent/claude-cowork/preload-cache/) · [ChatGPT](https://xspeedcache.com/agent/chatgpt/preload-cache/) · [Codex](https://xspeedcache.com/agent/codex/preload-cache/) · [Cursor](https://xspeedcache.com/agent/cursor/preload-cache/) · [GitHub Copilot in VS Code](https://xspeedcache.com/agent/github-copilot/preload-cache/) · [Windsurf](https://xspeedcache.com/agent/windsurf/preload-cache/) · [Gemini CLI](https://xspeedcache.com/agent/gemini-cli/preload-cache/) · [Antigravity](https://xspeedcache.com/agent/antigravity/preload-cache/) · [Zed](https://xspeedcache.com/agent/zed/preload-cache/) · [Kiro](https://xspeedcache.com/agent/kiro/preload-cache/) · [OpenCode](https://xspeedcache.com/agent/opencode/preload-cache/) · [OpenClaw](https://xspeedcache.com/agent/openclaw/preload-cache/) · [Hermes Agent](https://xspeedcache.com/agent/hermes-agent/preload-cache/) · [Grok Build](https://xspeedcache.com/agent/grok-build/preload-cache/) · [ChatGPT dots](https://xspeedcache.com/agent/chatgpt-dots/preload-cache/) · [Grok Bot](https://xspeedcache.com/agent/grok-bot/preload-cache/) · [Muse](https://xspeedcache.com/agent/muse/preload-cache/) · [Manus](https://xspeedcache.com/agent/manus/preload-cache/) · [Kimi Code](https://xspeedcache.com/agent/kimi/preload-cache/) · [Paperclip](https://xspeedcache.com/agent/paperclip/preload-cache/) · [NanoClaw](https://xspeedcache.com/agent/nanoclaw/preload-cache/)

## More with Grok

- [Purge the WordPress cache with Grok](https://xspeedcache.com/agent/grok/purge-cache/)
- [Find out why WordPress pages are not cached with Grok](https://xspeedcache.com/agent/grok/troubleshoot-cache/)
- [Scan a website for speed problems with Grok](https://xspeedcache.com/agent/grok/speed-scan/)
- [Run and track PageSpeed tests with Grok](https://xspeedcache.com/agent/grok/pagespeed-tests/)
- [Raise a WordPress site's PageSpeed score with Grok](https://xspeedcache.com/agent/grok/optimize-site/)
- [Tune WordPress cache settings with Grok](https://xspeedcache.com/agent/grok/cache-settings/)
- [Set up the Redis object cache with Grok](https://xspeedcache.com/agent/grok/object-cache/)
- [Manage Cloudflare caching with Grok](https://xspeedcache.com/agent/grok/cloudflare/)
- [Manage every WordPress site at once with Grok](https://xspeedcache.com/agent/grok/fleet/)

## Documentation

- How to warm your cache ahead of visitors: https://xspeedcache.com/docs/preloader/
- How to crawl your sitemap: https://xspeedcache.com/docs/crawl-now/
- How to enable Page Cache: https://xspeedcache.com/docs/page-cache/
- Managing your fleet with xSpeed Hub: https://xspeedcache.com/docs/managing-your-fleet-with-xspeed-hub/