automatelab-ai-seo
OfficialThis server provides a comprehensive AI-SEO audit toolkit for optimizing web pages for AI citation and visibility — no API keys required.
Auditing
audit_page— Full AI-SEO audit with an 8-dimension composite score (schema, technical, structure, robots, freshness, authority, entity density, sitemap) and ranked, actionable fix recommendations.audit_schema— Validate JSON-LD structured data against Schema.org rules and AI-citation best practices (supports URL or raw JSON).audit_canonical— Audit canonical link integrity,og:urlconsistency, trailing-slash hygiene, andhreflangimplementation.check_technical— Audit<head>tags: HTTPS, OpenGraph, Twitter Card,noindextraps, and title/H1 hygiene.
Crawler & Indexing
check_robots— Parserobots.txtand report per-crawler allow/disallow status for all known AI crawlers (GPTBot, ClaudeBot, PerplexityBot, etc.).check_sitemap— Validate XML sitemaps for presence, URL count,lastmodfreshness, and sitemap-index handling.
Scoring
score_ai_overview_eligibility— Score a page's probability of appearing in Google AI Overviews across six subscores (semantic completeness, structured data, E-E-A-T, entity density, freshness, technical hygiene).score_citation_worthiness— Score how citable a page or text block is for ChatGPT, Claude, Perplexity, and Google AI Overviews, optionally targeting a specific query.
Content Rewriting
rewrite_for_aeo— Rewrite content for Answer Engine Optimization: BLUF openings, FAQ structure, and schema additions for direct-answer AI surfaces.rewrite_for_geo— Rewrite content for Generative Engine Optimization: entity-rich, comparison-ready, synthesis-friendly format for Perplexity, Google AI Mode, etc.
llms.txt Tooling
generate_llms_txt— Generate a spec-compliantllms.txt(and optionallyllms-full.txt) for a domain from its sitemap.validate_llms_txt— Lint an existingllms.txtfor spec compliance, structural correctness, and broken links.
Entity & Comparison
extract_entities— Extract named entities,sameAsgraph nodes, and citation-density scores from a page's content and structured data.diff_pages— Compare two URLs side-by-side for AI citation-worthiness with dimension scores, gap analysis, and prioritized fix recommendations.
Score a page's probability of appearing in Google AI Overviews using current correlation factors and structured data heuristics.
Optimize pages for ChatGPT Search by validating AI-crawler allowlists, FAQ schema, and citation-worthiness scoring.
Check PerplexityBot access in robots.txt, score citation worthiness, and rewrite content for Answer Engine Optimization.
@automatelab/ai-seo-mcp
AI Citation Toolkit for the Model Context Protocol
Audit why AI systems do or do not cite your pages. MCP server. No API keys.
Works inside Claude, Cursor, Windsurf, Codex, and any MCP client that speaks stdio.
What it checks
AI crawler access - GPTBot, OAI-SearchBot, ClaudeBot, and PerplexityBot allowed or blocked in
robots.txtllms.txt- present, spec-compliant, links aliveStructured answer extraction - FAQ headings, BLUF paragraphs, answer-ready blocks
[[schema]] completeness - FAQPage, Article, Organization, Person; flags deprecated patterns
Entity clarity - named entity density and
sameAscoverage that help AI systems identify the subjectCitation formatting - canonical URL hygiene,
og:url,hreflang, noindex trapsSitemap freshness -
lastmodsignals that tell crawlers the page is current
Run an audit. Get a list of citation-blockers, ranked.
You: Run an AI-SEO audit on
https://automatelab.tech/launching-the-ai-seo-mcp/.
Result (truncated):
{
"url": "https://automatelab.tech/launching-the-ai-seo-mcp/",
"score": 61,
"grade": "C",
"dimension_scores": {
"schema": 45, "technical": 80, "structure": 40,
"robots": 90, "freshness": 85, "authority": 40,
"entity_density": 21, "sitemap": 100
},
"findings": [
{
"severity": "critical",
"category": "structure",
"message": "No FAQ structure found (no FAQPage schema or H3 question headings).",
"fix": "Add FAQ H3 headings ending in '?' with answer paragraphs, and a FAQPage JSON-LD block.",
"estimated_impact": "high"
},
{
"severity": "warning",
"category": "authority",
"message": "Low authority signals - missing Organization or author Person schema.",
"fix": "Add Organization JSON-LD and Article.author as a Person node with sameAs links.",
"estimated_impact": "high"
}
]
}Each finding names the exact fix. No opaque scores, no guesswork.
Install
npx -y @automatelab/ai-seo-mcpRequires Node 20 or later.
Claude Desktop
Add to %APPDATA%\Claude\claude_desktop_config.json (Windows) or ~/Library/Application Support/Claude/claude_desktop_config.json (macOS):
{
"mcpServers": {
"ai-seo": {
"command": "npx",
"args": ["-y", "@automatelab/ai-seo-mcp"]
}
}
}Restart Claude Desktop. Any MCP client that supports stdio transport works - same command / args pattern.
Optional: headless rendering for SPAs
By default audit_page reads raw HTML — fast, but misses content on React/Vue/Angular SPAs. Pass render: "headless" to spin up Chromium and audit the rendered DOM (adds 3-10s per audit).
One-time install:
npm install playwright-core
npx playwright install chromiumThen call audit_page with render: "headless". Use static for everything else — most marketing sites and docs render fine without it.
Further reading
automatelab.tech - teardowns and case studies
Tool | Purpose |
| Composite AI-SEO audit with 8-dimension scoring (schema, technical, structure, robots, freshness, authority, entity density, sitemap). |
| Validate JSON-LD against Schema.org rules and AI-citation best practice. Flags deprecated patterns. |
| Canonical link integrity, trailing-slash hygiene, |
| Single-call site sweep: |
| Site-wide content audit: stride-sample N URLs from the sitemap, run |
| Parse |
| Validate XML sitemaps: presence, URL count, |
| HEAD tag audit: canonical, OpenGraph, Twitter Card, hreflang, HTTPS, noindex, title hygiene. |
| Score a page's probability of appearing in Google AI Overviews using current correlation factors. |
| Score how citable a page or text block is for Perplexity, ChatGPT, Google AI Overviews, and Claude. |
| Simulate "would an AI engine cite this for this query?" via MCP sampling, with deterministic heuristic fallback. |
| Generate |
| Lint an existing |
| Rewrite content for Answer Engine Optimization (BLUF structure, FAQ format, schema additions). |
| Rewrite content for Generative Engine Optimization (entity definitions, comparison tables, synthesis-ready structure). |
| Extract named entities, |
| Compare two URLs for AI citation-worthiness: side-by-side dimension scores, gap analysis, and prioritized fix recommendations for url_a. |
| Render an |
v0.4.0 renamed tools from flat
snake_caseto dot-notation (audit.page,check.robots, …) for a navigable hierarchy. Update any saved invocations.
Environment variables: see ENV.md.
Contributing
Bug reports, feature ideas, and PRs welcome. See CONTRIBUTING.md.
Security
To report a vulnerability, see SECURITY.md.
License
MIT - see LICENSE.
Built by automatelab.tech
Maintenance
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/AutomateLab-tech/ai-seo-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server