# Warm the WordPress cache with Gemini CLI

> Warming the WordPress cache with Gemini CLI means asking it, in your terminal, to start the xSpeed preloader on a site through xSpeed Hub and to read back how far the crawl has got.

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

You run Gemini CLI from the project folder, and the release you just shipped has left the live site with a cold cache. You type which site to warm. Gemini CLI calls list_sites to match the handle and then start_preloader. The plugin on the site reads its sitemap and requests the pages in the background, so the first visitors after the release get stored pages.

Asked for progress, Gemini CLI calls get_preloader_status. That call is a read and reports whether a run is active and how far through the URL list it has got. If the crawl should stop, ask for stop_preloader and the pages already warmed stay cached. Gemini CLI names each Hub tool with the server first, as mcp_xspeedhub_start_preloader, so a rule can target the preloader writes on their own.

Gemini CLI shows a confirmation for an MCP tool call unless the server entry sets trust to true or you start it with --approval-mode=yolo (or --yolo), which approves every tool call. The prompt lets you proceed once, always allow that tool, always allow the whole xspeedhub server, or cancel, and the two always choices stop later prompts, so be careful with them here. Policy rules can also allow, deny or ask for a named tool by server and tool name. The Hub has no confirmation of its own and runs a start as soon as your connection allows writes, so the prompt is the check you see. Since the output stays in your scrollback, you can scroll back later and see which sites started and which refused, which is handy after a release that touched several.

## Set up Gemini CLI 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 to Gemini CLI

Run this once. --scope user writes the server to ~/.gemini/settings.json so it works in every project; without it Gemini CLI saves to the project's .gemini/settings.json, which is the default.

```bash
gemini mcp add --scope user --transport http xspeedhub https://app.xspeedcache.com/xspeed/mcp
```

### 3. Authenticate with /mcp auth

Start gemini and run /mcp auth xspeedhub. A browser page opens where you sign in to xSpeed Hub and approve access, and Gemini CLI receives the redirect on a local port. There is no token to paste, and the client keeps the credentials it receives. Run /mcp afterwards to check that xspeedhub shows as connected and lists its tools.

```
/mcp auth xspeedhub
```

Full setup: https://xspeedcache.com/agent/gemini-cli/

### 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. Gemini CLI shows a confirmation for an MCP tool call unless the server entry sets trust to true or you start Gemini CLI with --approval-mode=yolo (or --yolo), which approves every tool call. You can proceed once, always allow that tool, always allow the whole xspeedhub server, or cancel; the last two choices stop later prompts for those tools. Policy rules in ~/.gemini/policies can allow, deny or ask for a named tool by server and tool name. The Hub has no confirmation step of its own, so a trusted server, YOLO mode or an allow rule lets a write run as soon as your connection allows writes.

## Prompts

- Use xSpeed Hub to warm the shop site now that the release is out, then print the preloader status.
- Using xSpeed Hub, is the preloader on blog still running? If it is, stop it.
- With xSpeed Hub, warm every site in my workspace and list any that refused to start.

## Example session

```
You: Release shipped. Use xSpeed Hub to warm every site in the workspace.
  → list_sites [read-only]: 5 sites in this workspace
Agent: I will start the preloader on all 5 sites with one call, one after another. This touches every site. Proceed?
You: Yes, go.
  → start_preloader(site: all) [changes site]: 5 sites: 4 started, 1 refused because its preloader module is off
Agent: 4 crawls are running. The fifth site refused to start, so nothing is warming there until its preloader module is on.
```

## 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 Gemini CLI

Marking the xSpeed server as trusted in Gemini CLI's settings skips the prompt for every tool on it, including start_preloader and stop_preloader, and including a start across all sites. Starting Gemini CLI with --approval-mode=yolo (or --yolo) approves every tool call in the same way. That is convenient for status checks and a poor trade for writes. Leave trust off and skip yolo, or use the connection token with Read-only everywhere on (or a Viewer sign-in) for sessions where either is on, and answer the prompt for each preloader start yourself. Choosing always allow for the whole xspeedhub server has the same effect on the writes. A policy rule that allows only mcp_xspeedhub_get_preloader_status covers the read without widening anything else.

## 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

### Will Gemini CLI stop and ask before starting the preloader?

It asks before a tool call unless the server is marked as trusted in its settings or you started it with --approval-mode=yolo (or --yolo). The Hub runs start_preloader as soon as your connection allows writes, so that prompt is the check you rely on.

### Can I keep Gemini CLI from starting crawls at all?

Yes. List start_preloader and stop_preloader in excludeTools on the server entry and Gemini CLI never offers them, or write a deny rule for them. A read-only connection to the Hub (the connection token with Read-only everywhere on, or a Viewer sign-in) is the harder limit, because the Hub then refuses every write tool whatever the client sends.

### 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/) · [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](https://xspeedcache.com/agent/grok/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 Gemini CLI

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