原型 · 预览版：收录官方注册中心里的全部服务器，每 30 分钟同步一次。评价和账户功能将在后续阶段推出。
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚
新手模式 开
配色跟随系统浅色深色
语言ไทยEnglish中文日本語한국어EspañolDeutsch
☰ 菜单设置
新手模式 开
配色跟随系统浅色深色
语言ไทยEnglish中文日本語한국어EspañolDeutsch

squirrelscan

作者：squirrelscan版本 1.0.2i★ –i在云端运行
注册名称com.squirrelscan/squirrelscan

安装

概览

作者提供的说明（英文原文）

Website QA for your coding agent: audit SEO, performance, security, accessibility over MCP.

PopNx MCP 的三大支柱

这三项永远不会合并成一个分数：意见、测量和人气是不同的东西。

它能帮你做什么

我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。

  • 连接方式: 在云端运行
  • 传输方式: Streamable HTTP
  • 分类: 营销与社交媒体

安装

选择你使用的 AI 应用，然后复制设置。

安装之前

你需要

你用的是哪个应用？

在上方选择你的应用。我们会记住它，下次按钮会显示“安装到 …”。

适用于网页版、桌面版和手机版 Claude：

  1. 打开 Settings → Connectors
  2. 点击 Add custom connector
  3. 粘贴下面的地址，然后点击 Add
  4. 如果要求登录，请登录作者的服务
SettingsConnectors1+ Add2https://…3
https://mcp.squirrelscan.com/mcp

在终端中运行这条命令

claude mcp add --transport http squirrelscan https://mcp.squirrelscan.com/mcp

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json，或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "squirrelscan": {
      "url": "https://mcp.squirrelscan.com/mcp"
    }
  }
}

浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "squirrelscan": {
      "type": "http",
      "url": "https://mcp.squirrelscan.com/mcp"
    }
  }
}

浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。

ChatGPT 只能连接互联网上的服务器：

  1. 打开网页版 ChatGPT → Settings → Connectors (Apps)
  2. 点击 Create 或 Add（部分套餐需要先在 Advanced 中开启 Developer mode）
  3. 粘贴下面的地址，起个名字，然后保存
  4. 如果要求登录，请登录作者的服务
SettingsConnectors1+ Create2https://…3
https://mcp.squirrelscan.com/mcp

菜单名称可能因套餐和版本不同而略有差异。

你的选择通过 Cookie 保存在这台设备上，无需账户。

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同，请以 README 为准。

它能做什么

我们还没有读取这个服务器的工具列表；我们会轮流检查各个端点。

基础检查i

我们检查的是任何人都能看到的信息；我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月6日

  • ✓ 通过

    作者与仓库一致

    注册名称已通过域名 squirrelscan.com 验证（注册中心会核实域名所有权）

  • … 尚未检查

    仍在维护

    我们还没有从 GitHub 读取这个仓库

  • … 尚未检查

    有许可证

    我们还没有从 GitHub 读取这个仓库

  • … 尚未检查

    端点有响应

    尚未检查；我们会轮流检查各个端点

  • … 尚未检查

    使用 OAuth 登录

    尚未检查；我们会轮流检查各个端点

  • … 尚未检查

    工具描述中没有隐藏指令

    尚未检查；我们会在检查端点时读取工具列表

与“营销与社交媒体”中的其他服务器比较i

  • 星标数多于此分类中其他 2952 个服务器的 0%
  • 发布到注册中心的时间比此分类中其他 2952 个服务器的 19% 更新
  • 基础检查结果等于或优于此分类中其他 2952 个服务器的 100%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时，星标数才计入。

常见问题

squirrelscan 安全吗？

它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前，请先看看这个服务器要求哪些权限，并使用只具备所需权限的密钥。

它需要哪些密钥或代码？

注册中心没有列出必需的密钥，不过有些服务器会在首次使用时要求你登录。

它在我的电脑上运行还是在云端？

它在作者的云端运行。通过互联网连接，无需安装，但你发送的内容会经过作者的服务器。

它还在维护吗？

GitHub 仓库最后更新于–，最新版本（1.0.2）于4个月前进入注册中心。

哪些应用可以使用它？

支持 MCP 的应用，例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接，所以接受远程 MCP 服务器的应用也可以使用，例如开启开发者模式的 ChatGPT。

有什么可以替代它？

同一分类中有：MCP YouTube Transcript, Google Analytics MCP, BibiGPT YouTube Video Summarizer

替代选择

同一分类中其他作者的服务器，按星标数排序。

如何看卡片：★ GitHub 星标i三大支柱：评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

MCP YouTube Transcript

作者：jkawamoto

An MCP server retrieving transcripts of YouTube videos

在你的电脑上运行★ 495MIT9天前更新
安装

Google Analytics MCP

作者：surendranb

GA4 MCP server for AI agents: schema discovery, server-side aggregation, analysis-ready defaults.

在你的电脑上运行★ 244MIT9天前更新
安装

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

squirrelscan

The website QA tool for your coding agent

squirrelscan is an Open Source cli tool that audits websites for SEO, performance, security, accessibility, agent experience and other issues, and gives your coding agent exact fixes. Run it from the CLI, inside your coding agent, in the cloud, or over MCP.

Combine your coding agent with a deterministic and extensible audit tool.

A real run on a tiny test site, with the released CLI (signed out, so free) and Claude Code. We cut the two minutes the agent spent working, because nobody wants to watch an agent think.

Features

  • [Built for coding agents](https://docs.squirrelscan.com/developers/agents) - Skills for Claude Code, Cursor, Codex and any coding agent run the audit, fix and re-audit loop. Connect over the CLI, the hosted or local MCP server, or the API.
  • [Enriched fixes for you and your coding agent](https://docs.squirrelscan.com/guides/fix-your-site-with-an-ai-agent) - Every finding says how to fix it, in LLM-optimized output your agent can apply, and every rule has its own docs page. Signed in, the report adds an editor's summary of what to fix first and the technology stack the site runs on.
  • [300+ rules, 22 categories](https://docs.squirrelscan.com/rules) - Audit coverage across SEO, accessibility, performance, security, content and more.
  • [Agent experience](https://docs.squirrelscan.com/rules/ax) - Audit how well AI agents can read, discover and act on your site: llms.txt, AGENTS.md, Markdown responses, and what AI crawlers are served.
  • [Link checking and monitoring](https://docs.squirrelscan.com/guides/link-checking) - Perch, the cloud link checker, tells a broken link from a blocked one and confirms a failure before reporting it. On Pro and Team, scheduled audits email you when a link breaks.
  • [Security and site integrity](https://docs.squirrelscan.com/rules/integrity) - Detect phishing kits, injected pages, leaked credentials and missing security headers.
  • [Entity map](https://docs.squirrelscan.com/guides/entity-map) - Your site's JSON-LD collapsed into one graph: one identity, or a new one on every page.
  • [Browser rendering in the cloud](https://docs.squirrelscan.com/guides/browser-rendering) - Signed in, pages are rendered in a real browser in the cloud, so single-page apps and JavaScript-heavy sites are audited as visitors see them, at no extra cost per page.
  • [Cloud audits](https://docs.squirrelscan.com/guides/cloud-audits) - AI page analysis, scheduled audits, a per-website issue tracker and shareable reports.
  • [Smart crawling](https://docs.squirrelscan.com/crawl) - Fast and memory efficient, incremental with ETag, Last-Modified and content hashing, and resumable from checkpoints.
  • [Crawl history and changes](https://docs.squirrelscan.com/cli/report) - Track site evolution, compare crawls, spot regressions.
  • [Developer-first CLI](https://docs.squirrelscan.com/cli) - Single binary, zero dependencies, shell completions, self-update.
  • [Multiple output formats](https://docs.squirrelscan.com/cli/report#output-formats) - Console, JSON, HTML, Markdown, Text, LLM, XML.

Rule categories

Ordered by how much a failure usually costs you, not by how many rules each one has.

CategoryRulesWhat it covers
Crawlability21Whether search engines and agents can reach and index you at all: robots.txt, sitemap validity and coverage, indexability conflicts, redirect and canonical chains, soft 404s
Core SEO14The per-page fundamentals: title, meta description, H1, canonical, charset, doctype, robots meta, Open Graph and Twitter cards, plus canonical form drift across the site
Agent Experience17How ready you are for AI agents to read, discover and act on the site: whether GPTBot and Claude-User get the same content a browser does, AGENTS.md, llms.txt, Markdown responses, API and MCP discovery, licensing and noai signals, pay-per-crawl, response token weight
Site Integrity9Signs the site has been compromised: injected doorway pages, phishing kit signatures, obfuscated scripts, brand impersonation, cloaking, known-malicious URLs
Security23Transport and header hygiene: HTTPS and HSTS, CSP, cookie flags, mixed content, subresource integrity, leaked secrets, tokens in web storage, unprotected and downgraded forms, open GraphQL introspection and mutations over GET
Links14Internal and external link health: broken and dead links, in-page anchors whose target is gone, redirect chains, anchor-text quality, orphan and dead-end pages, pages linked only from sitewide chrome, HTTPS downgrades
Content25Text quality and honesty: common misspellings, duplicate titles and descriptions, title-template consistency, readability, word count, freshness, heading hierarchy, keyword stuffing, hidden text, placeholder media and contact details, encoding damage
Performance32Core Web Vitals and delivery: LCP, CLS and INP hints, TTFB, compression, caching, render-blocking resources, DOM size, font delivery, legacy and unminified JS/CSS
Reliability5Scripts, stylesheets and fonts that fail to load (a first-party bundle that answers 404 or 500 after a deploy, third-party and font failures), and forms that lose submissions
Images16Alt text, modern formats, responsive srcset, intrinsic dimensions and aspect-ratio mismatches, lazy loading above versus below the fold, file weight
Structured Data26JSON-LD validity and rich-result eligibility for Article, Product, FAQ, Review, Breadcrumb, Organization, LocalBusiness, Video and site search, the markup a page's classified type should carry, plus thirteen site-wide checks on the entity map: whether the site declares one identity for itself or a new one on every page, and rating markup that is not about the page it sits on
Accessibility61WCAG coverage: ARIA roles and names, form labels and autocomplete tokens, colour contrast, heading order, landmarks, tables and lists, focus visibility, touch targets, captions
Mobile8Viewport configuration, tap-target size, legible font sizes, horizontal scroll, blocked zoom, form fields small enough to zoom the page on focus, intrusive interstitials, the web app manifest and its icons
Social Media5Open Graph and Twitter Card completeness, image dimensions, canonical URL match, social profile links, site-chrome assets that disagree across pages
URL Structure9Length, casing, hyphenation, stop words, query parameters, special characters, trailing-slash consistency, site-wide convention consistency
E-E-A-T15Experience, expertise, authority and trust signals: author bylines and credentials, about and contact pages, citations, editorial policy, disclaimers, YMYL detection
Legal Compliance4Privacy policy, terms of service, real cookie-consent machinery, subprocessor disclosure
Internationalization2hreflang correctness and the document language declaration
Local SEO3NAP (name, address, phone) consistency across every crawled page, geo metadata, service-area businesses
Video3VideoObject markup, captions and accessibility, thumbnails
Analytics2Google Tag Manager presence and consent-mode wiring
Blocking3Content, links and trackers that ad blockers and privacy filters strip for a large share of your visitors

Total: 300+ rules across 22 categories

See the rules reference for full details.

CLI

Installation

Paste into your coding agent (Claude Code, Codex, Cursor, opencode and friends):

Fetch and follow the setup instructions for squirrelscan at https://docs.squirrelscan.com/agent-setup/prompt.md

Your agent installs the CLI, connects MCP and runs a first audit. You can read exactly what it will follow first.

macOS / Linux:

curl -fsSL https://install.squirrelscan.com | bash

Windows:

iwr -useb https://install.squirrelscan.com/install.ps1 | iex

Homebrew (macOS):

brew install --cask squirrelscan/tap/squirrel

The cask installs a launcher that runs the regular installer on first use. The CLI then updates itself with squirrel self update; brew upgrade leaves it alone.

npm (all platforms):

npm install -g squirrelscan

npx (run without installing):

npx squirrelscan audit example.com
Quick start
# Audit a website

squirrel audit example.com

Generate HTML report

squirrel audit example.com -f html -o report.html

Pipe to Claude for AI analysis

squirrel audit example.com --format llm | claude

Quick audit for a fast first look (other levels: surface, full)

squirrel audit example.com --level quick

run only agent experience and performance rules

squirrel audit example.com --rule-include ax,performance

login for cloud audits and cloud rendering

squirrel auth login

Reports

A health score and grade, group scores for SEO, performance, security and Agent Experience (AX) colored by score, a ranked list of issues, and a copy fix prompt for each one that you can paste into your coding agent. Publish reports to the web to share with team members or coding agents (fix instructions are embedded).

See an example report, or read how to read your report.

Add to your coding agent

squirrelscan ships as an MCP server (hosted at mcp.squirrelscan.com), skills (autonomous audit + fix workflows), and a plugin for Claude Code and Cursor. Cursor installs in one click from the badge above; the rest are a single copy-paste.

Cursor

Cl

只显示了开头部分；其余内容请在仓库中阅读

问 PopNx