Scan a website for speed problems with OpenCode

Scanning a site's speed with OpenCode means asking the open-source terminal agent to run an xSpeed Scan, and setting its permissions so the scan asks first while history reads do not.

list_sitesget_speed_scanrun_speed_scan

Last updated: October 2026

Example session · OpenCode

You: Using xSpeed Hub, what did shop score, and has it changed after my config edit? Scan if needed.

get_speed_scan(site: shop) read-only
→ Last scan two days ago: desktop grade B, mobile grade C

run_speed_scan(site: shop, fresh: true, strategy: both) uses quota
→ Desktop grade B, mobile grade B. Top remaining check: unoptimized images. Report link included.

OpenCode: Mobile moved from C to B since the scan two days ago. Desktop is unchanged. The remaining top check is unoptimized images. Report link is in the output.

How OpenCode handles this

OpenCode lets you decide per tool whether the agent asks, allows or denies, and a scan is a good case for using that, because most OpenCode permissions default to allow and run_speed_scan will start without a prompt until you add a rule. You ask it to scan a site. It calls run_speed_scan through xSpeed Hub, with a site handle, or through the no-account Scan MCP for any public URL, and prints a grade out of 100. The desktop run is the headline, the mobile run is graded beside it, and the ranked failing checks come with the report link.

The permissions are where it gets interesting. OpenCode checks MCP tools under the prefixed name, such as xspeedhub_run_speed_scan, and the last matching rule wins, so write an ask rule for xspeedhub_* first and then allow xspeedhub_get_*. Set get_speed_scan to allow, since reading a report or the scan history starts nothing and spends nothing. Set run_speed_scan to ask, because on the Hub it is classed as a write tool: each scan spends the shared speed-test allowance. The result is an agent that answers what did this site score for free and only stops to ask when you want a new measurement.

Because the Scan MCP is read-only in every tool, you can set it to allow in full. The only limit there is four scans per caller per ten minutes, and a re-scan of the same URL within that window returns the existing report unless the agent asks for a fresh one. Ask for the report link every time, so the answer in your terminal and the page you share are the same evidence.

Set up OpenCode once

Already connected? Skip to the prompts. Alternatives and troubleshooting are on the OpenCode 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 config

Put this block in your global config, or in opencode.json at a project root to scope it to that project. OpenCode reads both JSON and JSONC. No other field is needed: when the Hub answers 401, OpenCode starts the OAuth flow and registers itself through dynamic client registration.

~/.config/opencode/opencode.json

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "xspeedhub": {
      "type": "remote",
      "url": "https://app.xspeedcache.com/xspeed/mcp"
    }
  }
}

3Sign in with opencode mcp auth

Run this once. It opens a browser page on xSpeed Hub where you sign in and approve access. There is no token to paste; OpenCode stores the credentials it receives. Run opencode mcp list to see the server and its auth status, and opencode mcp debug xspeedhub if the connection fails.

Terminal

opencode mcp auth xspeedhub

4Add the xSpeed Scan MCP for sites you do not run

Prompts that scan a public URL use the xSpeed Scan MCP, a separate server from the Hub. Add it to OpenCode the same way as the Hub above, as a second server (xspeedscan, for example) with the URL https://xspeedcache.com/scan/mcp, and leave out any sign-in setting, such as an OAuth or auth option or an Authorization header, because the Scan MCP needs no account, token or sign-in. On a plan that allows one custom connector, add whichever server the prompts you use need.

Text

https://xspeedcache.com/scan/mcp

1 / 4

Full OpenCode 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. OpenCode checks MCP tools against its permission rules under the prefixed name, such as xspeedhub_purge_cache, and most permissions default to allow. With no rule of yours in place, a Hub write tool runs without a prompt. Add rules to change that: "xspeedhub_*": "ask" first, then "xspeedhub_get_*": "allow" and "xspeedhub_list_*": "allow", because the last matching rule wins. A deny rule holds even under opencode --auto, which approves everything that is not denied. The Hub itself has no confirmation step, so these rules and read-only access are the gates. For read-only access, send the connection token with Read-only everywhere on, or sign in as a Viewer member.

What do I ask?

Three prompts written for OpenCode. More for this job are below.

Prompt for OpenCode

Using xSpeed Hub, what did shop score last time? Read the scan history and do not start a new scan.

Prompt for OpenCode

Use xSpeed Hub to scan shop fresh and tell me whether the mobile grade changed since the last report.

Prompt for OpenCode

Use the xSpeed Scan MCP to scan this public URL and print the failing checks as a Markdown list.

What happens, step by step

An xSpeed Scan grades a site from 0 to 100 using server probes (time to first byte, compression, cache evidence, redirects, platform detection) plus a Lighthouse run, and names the fix for every failing check. An agent can start one two ways. Through xSpeed Hub, run_speed_scan scans a site you have connected. Through the no-account Scan MCP at https://xspeedcache.com/scan/mcp, it scans any public URL and cannot change anything. Either way you get a report link to share.

Check what the site already scored

get_speed_scan without a scan id returns the site's scan history, newest first, plus a summary of the latest report. It starts nothing and spends nothing, so the Hub tells the agent to read it first when you ask what a site scored.

Start a scan

run_speed_scan runs the full scan on a site you connected to the Hub. strategy is both (the default), desktop or mobile; one device alone costs half the engine's quota. The scan takes 20 to 60 seconds. The Hub waits about 50 seconds and, if the scan is still running, hands back a scan id.

Poll if it is still running

Call get_speed_scan with scan_id. While the scan runs it returns the running status and a note to ask again in about 20 seconds. The report page is live from the start and refreshes itself.

Read the result

The summary carries the grade, the four dimension scores, what was measured and the top fixes ranked by points recoverable, each with the xSpeed feature that fixes it. The headline grade is the desktop run. The mobile run is graded alongside it, so the agent should mention both when they differ.

Scan a site you do not run

For any other public URL, the agent uses the Scan MCP at https://xspeedcache.com/scan/mcp. There is no account and no sign-in. It takes a url, returns the same graded report and a link at xspeedcache.com/scan/r/<id>, and is limited to 4 scans per caller per 10 minutes.

Fix, wait, re-scan

After a change, wait several minutes and scan again with fresh: true. Without it, the scan service reuses any report from the last 10 minutes and the agent will show you the old number.

Reference

Hub route	run_speed_scan, then get_speed_scan with scan_id; only for sites connected to your Hub
Scan MCP route	https://xspeedcache.com/scan/mcp, no account, 5 tools, read-only, any public URL
Scan MCP limit	4 scans per caller per 10 minutes
Why run_speed_scan is a write	It spends a shared scan allowance and stores a report; it changes nothing on the site
Read-only Hub connection	run_speed_scan is refused; get_speed_scan still works. Applies to the connection token with Read-only everywhere on and to a Viewer sign-in; an OAuth sign-in gets the scopes the client asks for
Duration	20 to 60 seconds; the Hub waits about 50 seconds, then returns a scan id
Poll argument	scan_id on the Hub tool, scanId on the Scan MCP tool
strategy	both (default), desktop or mobile; one device costs half the quota and becomes the headline
fresh	true forces a new measurement; otherwise a report from the last 10 minutes is reused
Report link	xspeedcache.com/scan/r/<id>; add .md for a Markdown twin an agent can read
Report visibility	Hub scans are filed unlisted; Scan MCP scans are public in the scan directory by default

Rules worth keeping

Read before you spend. Ask for the scan history first; start a new scan only when you want a fresh measurement or something changed.
A report link is not private. An unlisted report is kept out of the scan directory and search, but anyone with the URL can open it. A scan started through the Scan MCP is public by default.
run_speed_scan changes nothing on your site, but the Hub classes it a write, so a read-only connection (the connection token with Read-only everywhere on, or a Viewer sign-in) refuses it and your client may prompt for it. Use get_speed_scan, or the Scan MCP for a public URL, when you want a strictly read-only route.
Compare like with like. A scan that lost its Lighthouse run is marked partial and is not comparable with a full one, and the lab grade is not the same as real-visitor Core Web Vitals, which the report shows separately.
A scan cannot reach private, local or password-protected sites, and a site behind a bot challenge returns a report that says its server checks were not measured.

Good to know with OpenCode

OpenCode starts from permissive defaults, so until you add an ask or deny rule for the xspeedhub_ tools, treat run_speed_scan as able to run on the model's say-so. A rule that denies the whole server will also deny the free history read. A deny rule holds even under opencode --auto, which approves everything that is not denied. If you run OpenCode in a script, a read-only Hub connection (the connection token with Read-only everywhere on, or a Viewer sign-in) is the sturdier guard, because it makes the Hub refuse run_speed_scan whatever the client rules say.

More prompts for this job

Prompts about your own sites work in any client connected to xSpeed Hub. A prompt that scans a site you do not run, or names the scan server, needs the xSpeed Scan MCP from the setup above.

Prompt

Using xSpeed Hub, what did the shop site score on its last speed scan? Do not start a new one.

Prompt

Use xSpeed Hub to run a speed scan on blog and give me the three fixes that recover the most points, plus the report link.

Prompt

With xSpeed Hub, scan only the mobile view of shop and tell me the grade.

Prompt

I changed the theme this morning. Use xSpeed Hub to run a fresh scan on docs and compare it with the previous report.

Prompt

Use the xSpeed Scan MCP to grade [competitor URL] and tell me what its biggest weaknesses are.

Prompt

The speed scan on shop is still running. Ask xSpeed Hub to check it again and tell me when it finishes.

Frequently asked questions

Allow get_speed_scan, since it only reads reports and history, and set run_speed_scan to ask, since each scan on the Hub spends the shared speed-test allowance. OpenCode allows most tools by default, so the ask rule has to be written first. The Scan MCP is read-only, so allowing all of its tools is reasonable.

Scanning the same URL again within ten minutes returns the existing report. If you changed something and want a new measurement, ask the agent for a fresh scan, which forces a new run.

run_speed_scan runs the full xSpeed Scan: server probes plus Lighthouse, a 0 to 100 grade across four dimensions, the fix for every failing check and a shareable report link. run_speed_test returns a raw PageSpeed Insights score with Core Web Vitals and no graded report.

Yes, through the xSpeed Scan MCP at https://xspeedcache.com/scan/mcp. It needs no account and no sign-in, accepts any public URL and is read-only. The Hub route only scans sites you connected to your own workspace.

The Scan MCP allows 4 scans per caller per 10 minutes. Scanning the same URL again within 10 minutes returns the existing report unless the agent passes fresh: true. A Hub scan spends a shared allowance of the scan service, which is why the Hub treats it as a write tool.

Reports started from the Hub are filed as unlisted, which keeps them out of the public scan directory and search results, but the link itself still opens for anyone who has it. Reports started through the Scan MCP are public by default.

The headline grade is the desktop run, because it is the one you can reproduce in your own browser. The mobile run is graded on the same rubric and returned alongside it. Google ranks on mobile, so when the two differ the agent should tell you both.

Keep going

Scan a site's speed with other agents

More with OpenCode

Purge the cache Find out why pages are not cached Track PageSpeed scores Raise the PageSpeed score Tune cache settings Warm the cache Set up Redis object cache Manage Cloudflare Manage every site at once

Documentation

From the blog

Scan a site's speed, from OpenCode.

xSpeed Hub is free and has no site cap. Connect your sites once and ask from the agent you already use.

Open xSpeed Hub OpenCode setup