TTokenySpace
返回 MCP 列表

squirrelscan

设计与创作

The website QA tool for your coding agent. 270+ audit rules across SEO, performance, security, accessibility and agent experience.

247TypeScriptv1.0.2远程托管更新于 2026/7/31
GitHub
0

远程接入地址

https://mcp.squirrelscan.com/mcp

介绍

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

README

squirrelscan

squirrelscan

The website QA tool for your coding agent

squirrelscan audits your website for SEO, performance, security, accessibility and agent experience issues, and gives your coding agent exact fixes. Run it from the CLI, inside your coding agent, in the cloud, or over MCP. Local audits are always free.

Add to Cursor Add to Claude Code Add to Codex Add to opencode MCP Registry

CI CodeQL npm License: MIT

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

Click the Add to Cursor badge above, or add it manually to ~/.cursor/mcp.json:

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

Skills: npx skills add squirrelscan/squirrelscan

Claude Code

Install the plugin (bundles skills + the MCP server):

/plugin marketplace add squirrelscan/squirrelscan
/plugin install squirrelscan@squirrelscan

Or add just the MCP server:

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

OpenAI Codex

Add the server to ~/.codex/config.toml:

[mcp_servers.squirrelscan]
url = "https://mcp.squirrelscan.com/mcp"

Codex reads Agent Skills from ~/.agents/skills, so skills work too: npx skills add squirrelscan/squirrelscan

opencode

Add the server to opencode.json:

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

Any MCP client

squirrelscan is in the MCP Registry as com.squirrelscan/squirrelscan. Point any client at the remote server:

https://mcp.squirrelscan.com/mcp

Authentication is per-user OAuth (or pass a squirrelscan API key as a Bearer token). Skills follow the Agent Skills standard: npx skills add squirrelscan/squirrelscan lands them in .agents/skills/.

Features

  • 260+ Rules, 21 Categories - Comprehensive coverage across SEO, accessibility, performance, and security
  • AI-Native Design - LLM-optimised output for Claude Code, Cursor, and any AI assistant
  • Smart Incremental Crawling - ETag, Last-Modified, content hashing. Resume from checkpoints.
  • Developer-First CLI - Single binary, zero dependencies, shell completions, self-update
  • E-E-A-T Auditing - Dedicated rules for Experience, Expertise, Authority, Trust
  • Crawl History & Changes - Track site evolution, compare crawls, spot regressions
  • Multiple Output Formats - Console, JSON, HTML, Markdown, Text, LLM, XML

CLI

Installation

macOS / Linux:

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

Windows:

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

npm (all platforms):

npm install -g squirrelscan

npx (run without installing):

npx squirrelscan audit example.com

Quick Start

# Audit a website
squirrel audit https://example.com

# Generate HTML report
squirrel audit https://example.com -f html -o report.html

# Pipe to Claude for AI analysis
squirrel audit https://example.com --format llm | claude

# Limit pages for faster results
squirrel audit https://example.com -m 10

Skills

Two skills drive agent workflows:

  • squirrelscan - operating the CLI: install, login, keys, credits, running audits, publishing reports, MCP setup, config, troubleshooting.
  • audit-website - the full fix loop: audit, map issues to source files, fix in batches, re-audit until the site scores well.
npx skills add squirrelscan/squirrelscan

Then, in your agent:

Use the audit-website skill to audit this site and fix all issues but only crawl 10 pages

Rule Categories

CategoryRulesFocus
Accessibility59ARIA, button/input names, landmarks, lists, tables, focus
Performance29Core Web Vitals, compression, caching, JS optimization
Crawlability18Robots.txt, sitemaps, indexability
Agent Experience17How ready a site is for AI agents to read, discover, operate
Security16HTTPS, CSP, cookies, leaked secrets
Images15Alt text, formats, lazy loading, optimization
E-E-A-T15Authority, trust, expertise signals
Links14Broken links, redirects, anchor text
Core SEO13Meta tags, canonical, doctype, charset
Content14Readability, freshness, word count, encoding, copyright year
Structured Data10JSON-LD, schema validation
Site Integrity9Injected pages, phishing kits, malware, SEO spam
URL Structure8Length, format, parameters
Mobile6Viewport, tap targets, responsive
Social Media4Open Graph, Twitter Cards
Legal Compliance4Privacy policy, cookie consent
Video3Schema, captions, thumbnails
Local SEO3NAP, geo tags, service areas
Blocking3Content, links, trackers that ad/privacy blockers block
Internationalization2Hreflang, lang attribute
Analytics2GTM, consent mode

Total: 264 rules across 21 categories

See the rules reference for full details.

Output Formats

FormatFlagUse Case
Console(default)Human-readable terminal output
JSON-f jsonCI/CD, programmatic processing
HTML-f htmlVisual reports for sharing
Markdown-f markdownDocumentation, GitHub
Text-f textClean output for piping to LLMs
LLM-f llmLLM optimized output

Development Status

squirrelscan is in active beta. Expect rapid iteration and breaking changes. Feedback and issue reports welcome!

Source and development

The complete local CLI, crawler, audit engine, rules, report generators, CLI-facing cloud clients, and documentation site are open source in this repository. The hosted API, website, dashboard, and cloud worker implementations are separate private services.

Prerequisites: Bun 1.3.14 and Git.

git clone https://github.com/squirrelscan/squirrelscan.git
cd squirrelscan
bun install --frozen-lockfile
bun run dev -- audit https://example.com --max-pages 10

Run the same checks used in pull requests:

bun run format:check
bun run lint
bun run typecheck
bun test
bun run build
bun run docs:check
bun run docs:build

See CONTRIBUTING.md before opening a pull request. Contributions require a Developer Certificate of Origin sign-off (git commit -s).

Telemetry

Telemetry is enabled by default and is deliberately minimal: event name, CLI version, a random install ID, and bounded error categories. It does not send credentials, URLs, report contents, or raw error messages, and telemetry requests are never authenticated.

Disable it permanently with:

squirrel self settings set telemetry false

Or disable all telemetry and install registration for any invocation by defining NO_TELEMETRY. Any defined value works, including an empty value, 0, or false:

NO_TELEMETRY=1 squirrel audit https://example.com

Links

License

The CLI and the repository contents are licensed under the MIT License. squirrelscan names and logos are covered by TRADEMARKS.md.

评论

加载中…

同类推荐