How Zed handles this
You are in Zed with the WordPress theme open, and the push has just emptied the cache on the live site. In the agent panel you write which site to warm. Zed's agent calls list_sites to match the handle and then start_preloader. The plugin on the site begins crawling the sitemap in the background, a few pages at a time, so that the first visitors get a stored page.
Asking for progress makes the agent call get_preloader_status, which reports whether a run is active and how far through the URL list it has got. If the crawl needs to end, ask for stop_preloader, and the pages already warmed stay cached. The whole exchange stays in the panel next to your code, with each tool call listed as its own step.
Zed's default for tool permissions is to confirm, and it confirms every call, reads included. So Zed will stop for get_preloader_status as well as for start_preloader and stop_preloader. That makes polling a crawl slower than in clients that let reads through, and it also means a preloader start never runs without you seeing it. The Hub has no confirmation of its own, so for this agent the Zed prompt does that work. A per-tool entry such as mcp:xspeedhub:get_preloader_status with a default of allow lets the status read through without a prompt. Since the agent panel keeps its history beside your code, a later look at the thread shows which sites you warmed and what each status said.
Set up Zed once
Already connected? Skip to the prompts. Alternatives and troubleshooting are on the Zed 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 as a remote server
Open Settings, then AI, then MCP Servers, click Add Server and choose Add Remote Server. Or run zed: open settings file and add the entry yourself. Zed calls MCP servers context servers, so the key is context_servers.
{
"context_servers": {
"xspeedhub": {
"url": "https://app.xspeedcache.com/xspeed/mcp"
}
}
} 3Sign in
Because the entry has no Authorization header, Zed prompts you to authenticate against the server with the standard MCP OAuth flow. Approve access on the xSpeed Hub page that opens. There is no token to paste. Back in Settings, AI, MCP Servers, a green dot beside xspeedhub with the tooltip Server is active means it is connected.
Settings → AI → MCP Servers
Full Zed 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. The Zed agent confirms before it runs any tool action. The default setting, agent.tool_permissions.default, is confirm, and that covers MCP tool calls, reads included. A per-tool entry such as mcp:xspeedhub:get_cache_status with a default of allow lets that one tool run without a prompt, and the Always for tool button in the prompt writes the same entry. Setting the global default to allow auto-approves every tool, writes included, and then a write reaches the Hub as soon as your connection allows writes. xSpeed Hub has no confirmation step of its own.
What do I ask?
Three prompts written for Zed. More for this job are below.
Use xSpeed Hub to warm the shop site and show me the preloader status once it has started.
Using xSpeed Hub, is the preloader still running on blog?
With xSpeed Hub, stop the preloader on shop, I need the server for a migration.
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.
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 Zed
Because Zed confirms every tool call by default, watching a crawl means answering a prompt each time you ask for status, which gets tedious over a long run. Add a per-tool entry that allows get_preloader_status, which the Always for tool button in the prompt does in one click, and leave start_preloader and stop_preloader on confirm. Do not set the global default to allow for this: it auto-approves every tool, the two preloader writes included. Zed documents per-tool entries for MCP tools and no wildcard, so each tool you allow is its own entry.
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
Keep going
Warm the cache with other agents
More with Zed
Documentation
- How to warm your cache ahead of visitors
- How to crawl your sitemap
- How to enable Page Cache
- Managing your fleet with xSpeed Hub
- How to write prompts for xSpeed Hub
- Zed + xSpeed
- Every AI agent that works with xSpeed
From the blog