MCP server for website health analysis — SEO, performance, accessibility, and security checks for any URL | 网站健康分析MCP服务器
If you already use Webcheck MCP, the webcheck mcp mcp server is the piece that lets your assistant work with it directly. MCP server for website health analysis — SEO, performance, accessibility, and security checks for any URL | 网站健康分析MCP服务器.
一个 MCP (Model Context Protocol) 服务器，让 AI 助手能够自动分析任意网站的 SEO、无障碍性、安全性和性能问题。
webcheck-mcp on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
check_website — Full health check: SEO score, performance, security headers, image analysischeck_seo — Deep SEO audit: title, meta, headings, content quality, Open Graph, structured datacheck_accessibility — Accessibility scan: alt texts, ARIA landmarks, heading hierarchy, form labelsfind_broken_links — Crawl all links on a page and report 404s, timeouts, and redirectscompare_pages — Side-by-side comparison of two URLs across all metricsTools — The Tools tool exposed by this serverFeatures — The Features tool exposed by this serverPlenty of search and retrieval servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Webcheck MCP's toolset — check_website, check_seo, check_accessibility and 4 more — is a fair guide to whether it matches your workflow. It is maintained by yifanyifan897645; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| check_website | Full health check: SEO score, performance, security headers, image analysis |
| check_seo | Deep SEO audit: title, meta, headings, content quality, Open Graph, structured data |
| check_accessibility | Accessibility scan: alt texts, ARIA landmarks, heading hierarchy, form labels |
| find_broken_links | Crawl all links on a page and report 404s, timeouts, and redirects |
| compare_pages | Side-by-side comparison of two URLs across all metrics |
| Tools | The Tools tool exposed by this server. |
| Features | The Features tool exposed by this server. |
{
"mcpServers": {
"webcheck": {
"command": "npx",
"args": ["-y", "webcheck-mcp"]
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
The simplest web tool that matters — fetch any URL and get model-ready markdown back.
Industrial-strength web extraction — render, scrape, crawl and search entire sites into clean markdown.
Puppeteer-powered browser control that drives pages from the accessibility tree instead of pixels.
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.
Put 6,000+ pre-built scrapers at your assistant's fingertips through one MCP endpoint.