Site Check
Public website health scan, AI-crawler and structured-data readiness, and a local presence score.
Connect it
Settings → Connectors → Add custom connector
URL: https://mcp.modernmustardseed.com/site-checkSettings → Apps & Connectors → Advanced → Developer mode
Create connector with URL: https://mcp.modernmustardseed.com/site-check{
"mcpServers": {
"site-check": {
"url": "https://mcp.modernmustardseed.com/site-check"
}
}
}claude mcp add --transport http site-check https://mcp.modernmustardseed.com/site-check{
"servers": {
"site-check": {
"type": "http",
"url": "https://mcp.modernmustardseed.com/site-check"
}
}
}4 tools, verified live
scan_websiteread-onlyRun a measured health check of a public website homepage: speed (server response, page weight, scripts, image formats), security (HTTPS, certificate expiry, security headers), domain registration expiry, email authentication (MX, SPF, DMARC), search basics (title, description, headings, indexability, sitemap), AI search readiness (structured data, AI crawler rules, llms.txt) and contact paths (tap
check_ai_search_readinessread-onlyCheck whether AI assistants and answer engines can read and quote a public website: which AI crawlers (GPTBot, ClaudeBot, PerplexityBot, Google-Extended and others) its robots.txt allows or blocks, whether it publishes llms.txt, which structured data types it declares, how its title and description read, and the search and AI checks with fixes. Shares the 24 hour cache with scan_website.
score_local_presenceread-onlyScore a local business on three pillars, website (45 percent), Google reviews (30 percent) and Google Business Profile (25 percent), and return an overall 0 to 100 score, a letter grade, each pillar with its verdict, and the top fixes. The website pillar comes from a live scan when a website is given. Review and profile facts (rating, review count, phone, address, hours) are supplied by the caller
explain_checkread-onlyExplain one Site Check check by its id (as returned by scan_website): what it measures, the pass and fail thresholds, why it matters, how to fix it, and the typical effort. Static reference, no network access.
Alternatives in Browser & Scraping
Compare →FOFouraA
Reliable web access for AI agents: smart HTTP, rotating proxies, and full-browser rendering.
HAHasDataB
All HasData scraping tools in one MCP server: Google, TikTok, Instagram, maps, e-commerce and more.
GAGatewayB
Durable self for AI agents: one-call resume, memory, real browser, free chat + hire real humans.
ZMZenrows MCPB
Zenrows MCP server — Fetch, Extract, Batch, and Browser Sessions for AI coding assistants
UNUnbrowseB
Websites as APIs: read pages, run site tasks via learned APIs, cloud browser with saved logins.
CMCrawlora MCPB
Hosted MCP: 3631 structured web-data tools across 471 platform groups.