# Warm the WordPress cache with Windsurf

> Warming the WordPress cache with Windsurf means asking its agent, in the editor you build the site in, to start the xSpeed preloader through xSpeed Hub and to report how far the crawl has got.

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

You are working on a WordPress theme in the editor, and the deploy has just emptied the cache on the live site. In the agent panel you ask for the site to be warmed. The agent calls list_sites to find the handle and then start_preloader on it, and the plugin starts crawling the sitemap in the background so visitors reach pages that are already stored.

Ask again for progress and the agent calls get_preloader_status, which says whether a run is active and how far through the URL list it has got. If the crawl needs to end early, ask for stop_preloader. Pages already warmed stay cached. None of this needs wp-admin, and a status check is a read, so it is safe to repeat while you carry on with your code.

Windsurf now ships as Devin Desktop. New tabs start with the Devin Local agent, and the older Cascade agent stays available for existing conversations. Devin Local prompts for approval before it calls any MCP tool, and the prompt lets you allow one tool or the whole xspeedhub server, for this session or permanently. Permission rules such as mcp__xspeedhub__get_preloader_status can allow, deny or always ask for a named tool. Smart mode lets a fast model run what it judges safe, and Bypass mode approves everything. The Hub adds no confirmation, so under either of those, or after you allow the whole server, start_preloader runs as soon as your connection allows writes. Since the status is a read, a quick check costs nothing, and it tells you whether the crawl you started is still going or has already finished its list.

## Set up Windsurf 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 for the Devin Local agent

Run this in a terminal. Devin Local shares its MCP configuration with Devin CLI, and -s user saves the server to ~/.config/devin/mcp_config.json (%APPDATA%\devin\mcp_config.json on Windows) so it applies to every project. Without -s, the command saves to local scope, which is the current project only.

```bash
devin mcp add -s user xspeedhub https://app.xspeedcache.com/xspeed/mcp
```

### 3. Sign in

Run the login command and approve access on the xSpeed Hub page that opens in your browser. There is no token to paste, and the client keeps the credentials it receives. If the server later shows Needs auth in the Devin Local MCP list, click Authenticate, or run devin mcp logout and then login again.

```bash
devin mcp login xspeedhub
```

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

### 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. The Devin Local agent prompts for approval before it calls any MCP tool. In the prompt you can allow that one tool or every tool on the xspeedhub server, for this session or permanently, and permission rules such as mcp__xspeedhub__get_cache_status allow, deny or always ask for a named tool. Smart mode lets a fast model run what it judges safe without a prompt, and Bypass mode approves everything, so with either of those a write reaches the Hub as soon as your connection allows writes. xSpeed Hub has no confirmation step of its own.

## Prompts

- The deploy finished. Use xSpeed Hub to warm shop and tell me what the preloader reports.
- With xSpeed Hub, check the preloader on blog and say whether it is still running.
- Use xSpeed Hub to stop the preloader on shop for now. I will start it again tonight.

## Example session

```
You: Use xSpeed Hub to warm the cache on shop, the theme is deployed.
  → start_preloader(site: shop) [changes site]: Queued 200 URLs from the sitemap; pages are fetched in the background
Agent: Started on shop. I will leave it running in the background.
You: Is it going?
  → get_preloader_status(site: shop) [read-only]: Running, 75 of 200 URLs warmed
Agent: 75 of 200 pages are warm and the crawl is still running.
```

## 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 Windsurf

Allow get_preloader_status with a rule and leave start_preloader and stop_preloader on the prompt. Allowing the whole xspeedhub server from the prompt lets both writes through, on any site the agent names. If the server shows Needs auth in the Devin Local MCP list, click Authenticate, or run the login again. Cascade can use at most 100 tools at a time across all your servers, so keep the list short enough that the 29 xSpeed tools are not cut off.

## 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

### Is Windsurf the same as Devin Desktop?

Yes. Windsurf now ships as Devin Desktop. New tabs start with the Devin Local agent, and the older Cascade agent remains for existing conversations. Devin Local prompts before any MCP tool call by default.

### Can the Windsurf agent warm all my sites at once?

Yes, by passing site: "all" to start_preloader. The Hub tells the agent to confirm with you once before it makes a call that touches every site, and it returns a result per site.

### 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/) · [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](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 Windsurf

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