How GitHub Copilot in VS Code handles this
You are in VS Code with a WordPress project open, and the change you were working on has just gone live. In Copilot's chat, in agent mode, you write which site to warm. Copilot reads the xSpeed tools it has been given, calls list_sites to find the handle, and then calls start_preloader. The plugin on the site starts requesting the sitemap's pages in the background, a few at a time.
VS Code starts in Manual permissions, which puts a confirmation in front of any tool call that is not auto-approved, so you see start_preloader before it runs. Afterwards you ask for progress and Copilot calls get_preloader_status, a read that reports whether a run is active and how many URLs are done. To end a crawl early, ask for stop_preloader. Pages already warmed stay cached.
A chat request can enable at most 128 tools, and the 29 xSpeed tools count toward that, next to any other servers you have enabled. If start_preloader is not offered, open the Configure Tools button in the chat input and check that the xSpeed tools are switched on. The Hub itself has no confirmation step. Chat: Manage Tool Approval lists tools grouped by MCP server, so you can trust get_preloader_status while the two preloader writes stay on a prompt. Allow all, Autopilot and global auto-approval skip the prompts, and then a start runs as soon as your connection allows writes. A good habit is to ask for the status before the start, so Copilot tells you whether a crawl is already running on that site and you do not begin a second one on top of it.
Set up GitHub Copilot in VS Code once
Already connected? Skip to the prompts. Alternatives and troubleshooting are on the GitHub Copilot in VS Code 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 to your user mcp.json
Open the Command Palette and run MCP: Open User Configuration, then add this entry. Servers in your user profile are available in every workspace. MCP: Add Server walks you through the same thing, and the project-level .mcp.json file works too if you want the entry shared with your team; that file uses a top-level mcpServers object instead of servers.
{
"servers": {
"xspeedhub": {
"type": "http",
"url": "https://app.xspeedcache.com/xspeed/mcp"
}
}
} 3Start the server and sign in
Run MCP: List Servers, pick xspeedhub and choose Start. VS Code asks whether you trust the server, then opens a browser page where you sign in to xSpeed Hub and approve access. There is no token to paste, and VS Code keeps the credentials it receives. Open the Chat view and use the Configure Tools button to see the xSpeed tools.
MCP: List Servers
Full GitHub Copilot in VS Code 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. In VS Code the default permission level is Manual permissions: a tool call that is not auto-approved shows a confirmation, and you can allow it once or for the session, the workspace or all future calls. Chat: Manage Tool Approval lists tools grouped by MCP server, so you can trust get_cache_status and the other reads while purge_cache and update_settings stay on a prompt. Allow all, Autopilot and global auto-approval skip those prompts, including for external tool calls, and then a write runs as soon as your connection allows writes. xSpeed Hub has no confirmation step of its own.
What do I ask?
Three prompts written for GitHub Copilot in VS Code. More for this job are below.
The deploy is done. Use xSpeed Hub to warm the shop site, then show me the preloader status.
Ask xSpeed Hub whether the preloader is running on blog and tell me how many URLs are left.
With xSpeed Hub, stop the preloader on docs, the server is busy with an import.
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 GitHub Copilot in VS Code
The confirmation lets you allow a tool once, or for the session, the workspace or all future calls. If you pick a wider scope for start_preloader, later requests start crawls without a dialog, which suits status checks and not writes. Trust get_preloader_status that way in Chat: Manage Tool Approval, and accept start_preloader and stop_preloader one at a time. Allow all and Autopilot skip the prompts for the preloader writes too.
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 GitHub Copilot in VS Code
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
- GitHub Copilot in VS Code + xSpeed
- Every AI agent that works with xSpeed
From the blog