Scan a website for speed problems with NanoClaw

Scanning a site's speed with NanoClaw means messaging your self-hosted agent in a chat app to run an xSpeed Scan, or scheduling one, and getting the grades and report link back in the thread.

list_sitesget_speed_scanrun_speed_scan

Last updated: October 2026

Example session · NanoClaw

You: @Andy use the xSpeed Scan MCP to grade rival-shop.example. They relaunched today.

run_speed_scan(url: rival-shop.example, strategy: both) read-only scan mcp
→ Desktop grade B, mobile grade C. Ranked fixes: image size, render-blocking stylesheet. Server response passes. Report link included.

NanoClaw: Desktop B and mobile C. Their server response passes now, so the slow first byte is gone. Images and one stylesheet hold mobile back. The report link is above.

You: @Andy and our shop?

get_speed_scan(site: shop) read-only
→ Latest report 5 days old: desktop grade B, mobile grade B

NanoClaw: shop scored B on both devices five days ago, so on mobile we are a grade ahead. I read the stored report and started no new scan.

How NanoClaw handles this

A link lands in your team's Slack: a prospect's site, or a competitor that just relaunched. You reply "@Andy use the xSpeed Scan MCP to grade this". If your agent group has the no-account xSpeed Scan MCP as a server, the agent calls run_speed_scan on the URL and posts a grade out of 100, desktop as the headline and mobile beside it, the top failing checks and a report link, in the same thread. The Scan MCP needs no credential, so you add it to the agent group with ncl groups config add-mcp-server and its HTTPS URL, leaving out the headers option, then restart the group.

For your own sites, the same agent group can reach xSpeed Hub with the connection token as a Bearer header. Then the agent reads a site's scan history with get_speed_scan, which spends nothing, and starts run_speed_scan by site handle when you want a fresh number. A Hub scan takes 20 to 60 seconds, and when one runs past about 50 seconds the Hub hands back a scan id for the agent to poll, so a chat reply may arrive in two parts.

Scheduled tasks turn this into a weekly habit. ncl tasks create runs a prompt on a cron schedule in the agent group's session, with no chat attached, so the prompt has to name where the report goes. A weekly competitor scan through the Scan MCP is a comfortable scheduled task, because every tool on that server is read-only. The Scan MCP allows four scans per caller per ten minutes, so a task covering more than a few URLs should be split into two tasks at different times.

Set up NanoClaw once

Already connected? Skip to the prompts. Alternatives and troubleshooting are on the NanoClaw 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 agent group

Copy the connection token from Connect AI in the Hub (only the workspace owner sees it). Then run this on the machine that hosts NanoClaw, with your agent group's ID from ncl groups list. The header goes in as a JSON object, because NanoClaw refuses credentials inside the URL. NanoClaw may ask an admin to approve the change.

Terminal

ncl groups config add-mcp-server --id <group-id> --name xspeedhub \
  --url https://app.xspeedcache.com/xspeed/mcp \
  --headers '{"Authorization":"Bearer <your connection token>"}'

3Restart the group and ask

The new server takes effect after a restart. Then message your agent with its trigger word, @Andy by default, and ask something that names xSpeed Hub.

Terminal

ncl groups restart --id <group-id>

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 NanoClaw 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 NanoClaw 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. Whether NanoClaw asks you before an MCP tool runs depends on how your fork and its admins are set up; its documentation gates adding a server behind approval but describes no per-tool prompt for calls. xSpeed Hub has no confirmation step of its own, so a write runs as soon as the agent calls it and your connection allows writes. The Hub tells the agent to confirm the target site and to ask once before a write that touches every site, which in NanoClaw shows up as a question in the chat. The firm stop is the token: with Read-only everywhere on, the Hub refuses every write tool. Keep it on for scheduled tasks.

What do I ask?

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

Prompt for NanoClaw

@Andy use the xSpeed Scan MCP to grade this URL and reply with the desktop and mobile grades and the report link.

Prompt for NanoClaw

@Andy with xSpeed Hub, tell me what shop scored on its last scan. Do not start a new one.

Prompt for NanoClaw

@Andy use xSpeed Hub to run a fresh scan on blog and tell me if mobile moved since the last report.

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 NanoClaw

On the Hub, run_speed_scan is a write tool, because every scan spends the shared speed-test allowance, and whether NanoClaw prompts before an MCP call depends on your fork. xSpeed Hub has no confirmation step of its own, so a scheduled task that calls run_speed_scan spends the allowance each time it fires. With Read-only everywhere on, the Hub refuses run_speed_scan and still answers get_speed_scan, which suits a scheduled report on your own sites. The switch belongs to the token, so every agent group that sends it gets the same scope. A scan runs from the xSpeed servers, so a site on your home network or behind a password cannot be graded, even though NanoClaw itself runs on your machine. Scans through the Scan MCP are public in the scan directory by default, so a competitor scan leaves a report anyone with the link can open.

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

Yes. Add the xSpeed Scan MCP to your agent group, which needs no credential, and ask with the trigger word. The agent posts the grades and the report link in the same chat. The limit is four scans per caller per ten minutes.

Yes, with ncl tasks create and a cron schedule. Name the chat that should get the report. On a read-only token the task can read each site's latest scan but not start a new one, because the Hub classes run_speed_scan as a write.

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 NanoClaw

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 NanoClaw.

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

Open xSpeed Hub NanoClaw setup