SEO Audit MCP Server

Analyze a single web page for SEO factors including:

• Meta tags (title, description, canonical, robots)

• Heading structure (H1-H6)

• Structured data (JSON-LD, with special focus on JobPosting schema)

• JavaScript rendering analysis (CSR vs SSR detection)

• Link analysis (internal, external, nofollow)

• Image analysis (alt tags, lazy loading)

• Mixed content detection

• Basic load time measurement

Use this for detailed analysis of specific pages like job detail pages, landing pages, or homepage.

Crawl multiple pages of a website starting from a URL. Discovers internal links and analyzes each page.

Returns:

• Aggregated statistics (pages with titles, meta descriptions, schema, etc.)

• Page type classification (job detail, category landing, location pages, etc.)

• Duplicate detection (titles, descriptions)

• Critical issues and warnings

• All individual page analyses

Use this for comprehensive site audits. Respects crawl limits and delays.

Run a Lighthouse performance audit on a URL.

Returns:

• Performance, Accessibility, Best Practices, and SEO scores

• Core Web Vitals (LCP, CLS, TBT/INP proxy, FCP, TTFB)

• Optimization opportunities with estimated savings

• Diagnostics (long tasks, layout shifts, etc.)

• SEO audit results (crawlability, meta tags, etc.)

Use this for performance analysis. Run separately for mobile and desktop if both matter.

Note: Requires Lighthouse CLI to be installed (npm install -g lighthouse).

Analyze a site's robots.txt and XML sitemaps.

Returns:

• robots.txt rules and any blocking issues

• All discovered sitemaps (from robots.txt and common locations)

• URL counts and job-specific URL detection

• Sitemap freshness analysis

• Recommendations for job boards (Indexing API, job sitemaps)

Use this as a first step to understand site structure before crawling.

Check HTTP status codes for a list of URLs.

Returns status code, redirect destination (if redirected), and response time for each URL.

Use this to:

• Verify expired job pages are handled correctly

• Check for broken links

• Analyze redirect chains

RECOMMENDED FIRST STEP - Analyze sitemaps and create an intelligent sampling strategy for large sites.

This tool is essential for job boards and large sites with 100k+ pages. Instead of crawling everything, it:

1. Discovers and validates all sitemaps (robots.txt + common locations)

2. Identifies distinct route patterns (job pages, category pages, location pages, etc.)

3. Estimates total pages per route type

4. Generates a smart sampling strategy

5. Recommends which pages to analyze with Lighthouse

Returns:

• Sitemap validation (URL limits, lastmod coverage, compression)

• Route pattern classification with estimated counts

• Sampling strategy (how many pages to sample per type)

• Issues, warnings, and recommendations

Use this BEFORE crawl_site or sample_pages to understand site structure.

Intelligently sample and analyze pages based on an audit plan.

Use this AFTER plan_audit to analyze representative pages from each route type.

For a site with 500k job pages, instead of crawling all of them, this will:

• Sample 30-50 job detail pages (random + oldest + newest)

• Sample 10-20 category landing pages

• Sample 10-20 location pages

• Sample company pages, static pages, etc.

Returns:

• Detailed analysis of each sampled page

• Aggregated issues per route type

• Cross-cutting findings (% missing titles, schema errors, etc.)

• Common issues ranked by frequency

This approach finds template-level issues that affect all pages of that type.

FULL AUDIT - Run a complete SEO audit with automatic sampling, caching, and report generation.

This is the main audit tool that orchestrates the entire workflow:

1. Discovers and analyzes sitemaps

2. Identifies route patterns and creates sampling strategy

3. Captures sample pages (cached - only fetches once)

4. Analyzes SEO, structured data, technical issues, social graph

5. Generates prioritized recommendations

6. Saves everything to reports/[sitename]/ folder

The audit captures pages ONCE and stores:

• HTML snapshots for inspection

• Full analysis data as JSON

• Final report as JSON + Markdown

Returns comprehensive findings and prioritized fix recommendations.