Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

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

claude mcp add --transport http webspeed https://api.webspeed.pro/mcp

[mcp_servers.webspeed]
url = "https://api.webspeed.pro/mcp"

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "webspeed": {
      "type": "remote",
      "url": "https://api.webspeed.pro/mcp",
      "enabled": true
    }
  }
}

{
  "mcpServers": {
    "webspeed": {
      "type": "http",
      "url": "https://api.webspeed.pro/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=webspeed&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vYXBpLndlYnNwZWVkLnByby9tY3AifQ%3D%3D"
}

{
  "servers": {
    "webspeed": {
      "type": "http",
      "url": "https://api.webspeed.pro/mcp"
    }
  }
}

{
  "mcpServers": {
    "webspeed": {
      "httpUrl": "https://api.webspeed.pro/mcp"
    }
  }
}

extensions:
  "webspeed":
    enabled: true
    name: "webspeed"
    type: streamable_http
    uri: "https://api.webspeed.pro/mcp"
    timeout: 300

Quality 88 / 100good

protocol75 · weight 25

warn
protocol.modernnewest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
n/a
protocol.statelessonly applies to 2026-07-28 servers
pass
protocol.transportstreamable HTTP
n/a
protocol.list_ttlonly applies to 2026-07-28 servers

authorizationn/a · weight 15

n/a
auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
n/a
auth.secret_in_urlno templated URL

tool hygiene94 · weight 30

pass
tools.descriptionsevery tool has a description
pass
tools.description_lengthdescriptions are concise
pass
tools.schemasevery tool has an object input schema
pass
tools.annotations5 of 5 tools declare readOnlyHint or destructiveHint
warn
tools.directory_hints1 of 5 tools declare all four hints; missing: explain_metric (idempotentHint); platform_benchmark (idempotentHint); find_research (idempotentHint); …
pass
tools.token_costabout 898 tokens to load every tool
pass
tools.api_dumptools are not a one-to-one API dump
pass
tools.hidden_textno hidden text in tool names, descriptions, schemas or annotations

stability100 · weight 15

pass
stability.changes3 tool changes in 30 days
pass
stability.rug_pullno tool changed its meaning under the same name
pass
stability.new_linksno tool change named a new site

dependenciesn/a · weight 15

n/a
deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

5 tools, about 898 tokens to load them all · tool set ef7241e960ac · tools last changed 2026-11-13 · checked 2026-11-14 06:30 UTC

Tool changes

2026-11-13find_researchadded
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.
2026-11-13platform_benchmarkadded
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.
2026-11-13explain_metricadded
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: list_changes · trend: quality JSON.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 82 / 100

no-repository

provenance55

liveness99

freshness100

hygiene80

+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. How it is computed.

Endpoints

remote	auth	reachable	uptime 30d	p50	protocol	last ok
`https://api.webspeed.pro/mcp` streamable-http	none	yes	99%	796 ms	2025-11-25	2026-11-14

Tools (5)

`explain_metric`read-only	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`read-only	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`read-only	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`read-only	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.

Schemas: list_tools.

Similar MCP servers

Official server.json

{
  "name": "pro.webspeed/webspeed",
  "icons": [
    {
      "src": "https://webspeed.pro/favicon.svg",
      "sizes": [
        "any"
      ],
      "mimeType": "image/svg+xml"
    }
  ],
  "title": "WebSpeed",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://api.webspeed.pro/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "1.0.3",
  "websiteUrl": "https://webspeed.pro/en/apps/",
  "description": "Measure a page with PageSpeed Insights and compare it with its copy sped up by WebSpeed Fast."
}