Home » Ai » 13-tool MCP server brings AI-SEO audits into Claude

13-tool MCP server brings AI-SEO audits into Claude

Cagri Sarigoz

Published May 16, 2026

Standard SEO tools track backlinks and keyword density. They don’t tell you whether a page will get cited by Perplexity, ChatGPT, or Google AI Overviews. @automatelab/ai-seo-mcp is a 13-tool MCP server built to fill that gap, and it runs directly inside Claude with no browser extension or SaaS dashboard involved.

What the 13 Tools Cover

The server organizes its tools across four categories:

• Audit: audit_page for full on-page AI-SEO analysis (headings, FAQ blocks, entity density, structured data), audit_schema for Schema.org validation and deprecation checks, and audit_canonical for canonical tag and redirect chain inspection.
• Technical: check_robots parses robots.txt and checks AI-crawler directives for GPTBot, ClaudeBot, and PerplexityBot. check_sitemap checks structure, freshness, and coverage. check_technical surfaces Core Web Vitals and crawlability flags.
• Scoring: score_ai_overview_eligibility predicts likelihood of inclusion in Google AI Overviews. score_citation_worthiness produces a composite score for LLM citation probability.
• Content: generate_llms_txt and validate_llms_txt handle the emerging llms.txt spec. extract_entities pulls named entities and semantic clusters. rewrite_for_aeo and rewrite_for_geo rewrite passages for Answer Engine and Generative Engine Optimization respectively.

Setup

Add the server to your claude_desktop_config.json (also works with Cursor and Cline):

{
  "mcpServers": {
    "ai-seo": {
      "command": "npx",
      "args": ["-y", "@automatelab/ai-seo-mcp"]
    }
  }
}

Or test it without a config change: npx -y @automatelab/ai-seo-mcp

What an Audit Looks Like

Ask Claude to audit a page and audit_page returns output inside your existing conversation. The developer shared an example result for their own site:

AI-SEO audit: automatelab.tech/n8n-mcp-server/
Citation worthiness: 72/100
FAQ block present: yes (4 questions)
Structured data: HowTo schema detected, no deprecation issues
Entity density: moderate – consider adding more named tools/versions
H2 headings: 6 match common query phrasing
AI-crawler access: GPTBot allowed, PerplexityBot allowed, ClaudeBot allowed
Top recommendation: Add a direct-answer paragraph in the first 150 words. AI Overviews pull from the top of the page first.

From there, you can call rewrite_for_aeo on the intro block and re-audit in the same session without switching tabs.

What’s Coming

The next version adds per-tool caching so repeated audits on the same URL skip re-fetching, and a batch_audit tool for running a full site check against a sitemap.

Repo: github.com/AutomateLab-tech/ai-seo. Landing page: automatelab.tech/products/mcp/ai-seo.

Cagri Sarigoz( Founder )

I’m founder of BizStack at Cagri Sarigoz LLC and a passionate advocate for entrepreneurs.

With over 14 years in tech, marketing, and AI, including my role as Head of SEO at CitizenShipper and co-founder of TaleBot at Intale AI, I’m dedicated to sharing genuine, useful product insights and tips.

At BizStack, I aim to cut through the digital noise to provide clear, actionable advice.

And more than all else, I’m a father to a (always) little girl and a husband.

Contact me at [email protected] for assistance.