# WebSpeed

> Measure a page with PageSpeed Insights and compare it with its copy sped up by WebSpeed Fast.

- name: pro.webspeed/webspeed
- version: 1.0.3
- connection class: R0 (autonomous)
- trust: 82/100 flags: no-repository
- quality: 88/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/pro.webspeed%2Fwebspeed
- tools: https://api.protogrid.dev/v1/servers/pro.webspeed%2Fwebspeed/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "webspeed": {
      "type": "http",
      "url": "https://api.webspeed.pro/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 99
- freshness: 100
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-99% +updated-17d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 88/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 94 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 5 of 5 tools declare readOnlyHint or destructiveHint
- warn `tools.directory_hints`: 1 of 5 tools declare all four hints; missing: explain_metric (idempotentHint); platform_benchmark (idempotentHint); find_research (idempotentHint); …
- pass `tools.token_cost`: about 898 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump
- pass `tools.hidden_text`: no hidden text in tool names, descriptions, schemas or annotations

### stability: 100 (weight 15)

- pass `stability.changes`: 3 tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name
- pass `stability.new_links`: no tool change named a new site

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 5, about 898 tokens to load them all
- tool set hash: ef7241e960ac9b4596f2ec4a0e72039b
- tools last changed: 2026-11-13T10:00:52.776Z
- badge: [![protogrid quality](https://protogrid.dev/badge/pro.webspeed/webspeed.svg)](https://protogrid.dev/servers/pro.webspeed/webspeed)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-11-13 `find_research` added
  - Findings of WebSpeed studies measured on real sites, each with its sample size, measurement date and caveats: why the PageSpeed score changes between runs, whether WooCommerce slows WordPress down, what plugins, fonts, images or third-party tags cost, PageSpeed by platform, and more. Use when the user asks a "why" or "does X slow my site" question about page speed or PageSpeed scores.
- 2026-11-13 `platform_benchmark` added
  - What typically slows sites on a website platform down (WordPress, WooCommerce, Squarespace, Wix, Duda, Tilda, Divi, Bitrix), measured across the WebSpeed audit base: the share of audited sites of that platform with each bottleneck, the number of audits and the snapshot date, plus published before/after teardowns and studies for the platform. Use when the user asks why their Squarespace / WordPress / … site is slow, what is normal for the platform, or what they can fix on it.
- 2026-11-13 `explain_metric` added
  - What a page-speed metric or term means, its good / needs-improvement / poor thresholds, and how real sites score on it: the median and the share of sites within the "good" line across the WebSpeed audit base (mobile lab runs of thousands of original sites), with the sample size and snapshot date. Also how many sites apply a technique such as fetchpriority, lazy loading or font-display. Use when the user asks whether a value is good or bad ("is an LCP of 4 s bad?"), what LCP / CLS / TBT / INP / TTFB / Speed Index / PageSpeed score means, or how other sites compare.

Full history: https://api.protogrid.dev/v1/servers/pro.webspeed%2Fwebspeed/changes

## Remotes

- https://api.webspeed.pro/mcp (streamable-http, auth none, reachable true, uptime30d 0.98507464)

## Packages

_none_

## Tools (5)

- `explain_metric`: What a page-speed metric or term means, its good / needs-improvement / poor thresholds, and how real sites score on it: the median and the share of sites within the "good" line across the WebSpeed audit base (mobile lab runs of thousands of original sites), with the sample size and snapshot date. Also how many sites apply a technique such as fetchpriority, lazy loading or font-display. Use when the user asks whether a value is good or bad ("is an LCP of 4 s bad?"), what LCP / CLS / TBT / INP / TTFB / Speed Index / PageSpeed score means, or how other sites compare.
- `find_research`: Findings of WebSpeed studies measured on real sites, each with its sample size, measurement date and caveats: why the PageSpeed score changes between runs, whether WooCommerce slows WordPress down, what plugins, fonts, images or third-party tags cost, PageSpeed by platform, and more. Use when the user asks a "why" or "does X slow my site" question about page speed or PageSpeed scores.
- `get_measurement`: Status or result of a measurement started with measure_site. While running, returns the queue position or progress. When done, returns the verified comparison and what else slows the page down. Quote numbers only from this result and keep its wording about estimates; if it says there is nothing to judge, do not invent numbers.
- `measure_site`: Start a real PageSpeed Insights measurement of a web page: the original site vs. its copy accelerated by WebSpeed Fast (mobile and desktop). Returns an audit_id immediately; the run takes 2–5 minutes, and get_measurement reads it when the user asks. If the page was measured before, its full result is returned at once. Results are published as a report page on webspeed.pro. Use when the user asks why a site is slow, how fast it is, or what can be sped up.
- `platform_benchmark`: What typically slows sites on a website platform down (WordPress, WooCommerce, Squarespace, Wix, Duda, Tilda, Divi, Bitrix), measured across the WebSpeed audit base: the share of audited sites of that platform with each bottleneck, the number of audits and the snapshot date, plus published before/after teardowns and studies for the platform. Use when the user asks why their Squarespace / WordPress / … site is slow, what is normal for the platform, or what they can fix on it.