AutomateLab-tech/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**Audit why AI systems do or do not cite your pages.** MCP server.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.txt
- **llms.txt** - present, spec-compliant, links alive
- **Structured answer extraction** - FAQ headings, BLUF paragraphs, answer-ready blocks
- **[[schema]] completeness** - FAQPage, Article, Organization, Person; flags deprecated patterns
- **Entity clarity** - named entity density and sameAs coverage that help AI systems identify the subject
- **Citation formatting** - canonical URL hygiene, og:url, hreflang, noindex traps
- **Sitemap freshness** - lastmod signals 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):
Each finding names the exact fix. No opaque scores, no guesswork.
---
Install
Requires 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):
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:
Then call audit_page with render: "headless". Use static for everything else — most marketing sites and docs render fine without it.
---
Run it in CI (GitHub Action)
This repo doubles as a GitHub Action. Drop it in a workflow to fail a PR when any page regresses below an AI-citation score - the same audit engine, gated on every change.
The Action builds the auditor from the pinned ref, runs audit_page on each URL, writes a scorecard to the job summary, and exits non-zero if any URL falls below min-score (when fail-on-regression is true). Outputs: min_score_observed, urls_audited, report_path. Full example: examples/github-action-usage.yml.
---
Further reading
- automatelab.tech - teardowns and case studies
---
MCP tool surface (20 tools)
| Tool | Purpose |
|------|---------|
| audit_page | Composite AI-SEO audit with 8-dimension scoring (schema, technical, structure, robots, freshness, authority, entity density, sitemap). |
| audit_schema | Validate JSON-LD against Schema.org rules and AI-citation best practice. Flags deprecated patterns. |
| audit_canonical | Canonical link integrity, trailing-slash hygiene, og:url consistency. |
| audit_site | Single-call site sweep: audit_page + check_robots + check_sitemap + audit_schema with overall grade and top-5 fixes. |
| audit_sitemap | Site-wide content audit: stride-sample N URLs from the sitemap, run audit_page on each, return distribution + worst pages + top findings. |
| check_robots | Parse robots.txt and report per-crawler allow/disallow for all known AI crawlers. Surfaces the GPTBot-blocked-but-OAI-SearchBot-allowed trap. |