Ai Seo

io.github.AutomateLab-techPublished by GitHub account AutomateLab-techv0.1.1Updated Oct 24, 2026

MCP server for AI-SEO auditing: schema, robots.txt, llms.txt, citation scoring, and AEO/GEO rewrites

VerifiedSTDIODesktop onlyWeb Search & ScrapingDeveloper ToolsData & Analytics

Overview

AI-generated overview

Local MCP server that audits web pages for AI-search visibility: schema, robots.txt, llms.txt, citation scoring and AEO/GEO rewrites.

What you can do
  • Audit pages and sites for AI-citation readiness, with 8-dimension scoring, ranked findings and concrete fixes
  • Check crawler access and indexing signals: robots.txt rules for AI crawlers, sitemaps, canonical tags, OpenGraph, hreflang and noindex
  • Validate and generate llms.txt files, and lint existing ones for spec compliance and broken links
  • Score citation worthiness, AI Overview eligibility, agentic browsing readiness, and simulate whether an engine would cite a page
  • Extract named entities and sameAs links, compare two URLs, and rewrite content for answer-engine and generative-engine optimization
  • Save audit results as Markdown reports to disk
When to use it
Useful when you publish web content and want to know why AI assistants and search engines do or do not cite your pages, or when you want repeatable AI-SEO checks in a CI workflow. Also handy for validating structured data, robots.txt and llms.txt before launch.
Requirements
Runs locally over stdio via npx (Node 20 or later); no API keys. Optional headless rendering for JavaScript-heavy sites needs playwright-core plus a Chromium install. Report saving writes under the MCP_WORKSPACE_ROOT directory.
Before you install
Audits fetch the target URLs, so the pages you point it at are requested from your machine. Rewrite tools produce new content that you should review before publishing. Report saving writes files to disk under the configured workspace root. Tool names changed in v0.4.0, so saved invocations may need updating.

Installation

In SourceWeft

  1. Open Ai Seo in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

@automatelab/ai-seo-mcp

AI Citation Toolkit for the Model Context Protocol

[npm version] [license] [node]

Audit why AI systems do or do not cite your pages.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):

json
{  "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

bash
npx -y @automatelab/ai-seo-mcp

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):

json
{  "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:

bash
npm install playwright-corenpx playwright install chromium

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.

yaml
- uses: actions/checkout@v4- name: AI-SEO audit  uses: AutomateLab-tech/[email protected]  with:    urls: "https://example.com,https://example.com/pricing"    min-score: "70"            # fail if any URL scores below this    respect-robots: "true"     # set false for staging / sites you own    report-path: "ai-seo-report.md"   # optional Markdown report artifact    fail-on-regression: "true"

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

MCP tool surface (20 tools)
ToolPurpose
audit_pageComposite AI-SEO audit with 8-dimension scoring (schema, technical, structure, robots, freshness, authority, entity density, sitemap).
audit_schemaValidate JSON-LD against Schema.org rules and AI-citation best practice. Flags deprecated patterns.
audit_canonicalCanonical link integrity, trailing-slash hygiene, og:url consistency.
audit_siteSingle-call site sweep: audit_page + check_robots + check_sitemap + audit_schema with overall grade and top-5 fixes.
audit_sitemapSite-wide content audit: stride-sample N URLs from the sitemap, run audit_page on each, return distribution + worst pages + top findings.
check_robotsParse robots.txt and report per-crawler allow/disallow for all known AI crawlers. Surfaces the GPTBot-blocked-but-OAI-SearchBot-allowed trap.
check_sitemapValidate XML sitemaps: presence, URL count, lastmod freshness, image/video extensions.
check_technicalHEAD tag audit: canonical, OpenGraph, Twitter Card, hreflang, HTTPS, noindex, title hygiene.
score_ai_overview_eligibilityScore a page's probability of appearing in Google AI Overviews using current correlation factors.
score_citation_worthinessScore how citable a page or text block is for Perplexity, ChatGPT, Google AI Overviews, and Claude. Includes per-section chunk_analysis / extractability_score: how cleanly an LLM can lift a standalone answer from each heading.
score_agentic_browsingScore a page against the Lighthouse "Agentic Browsing" category (May 2026): llms.txt, WebMCP, accessibility-tree integrity, and layout stability.
score_test_citationSimulate "would an AI engine cite this for this query?" via MCP sampling, with deterministic heuristic fallback.
llms_txt_generateGenerate llms.txt and optionally llms-full.txt from a domain's sitemap.
llms_txt_validateLint an existing llms.txt for spec compliance and broken links.
rewrite_aeoRewrite content for Answer Engine Optimization (BLUF structure, FAQ format, schema additions).
rewrite_geoRewrite content for Generative Engine Optimization (entity definitions, comparison tables, synthesis-ready structure).
extract_entitiesExtract named entities, sameAs links, and citation-density score from a page's content and structured data.
diff_pagesCompare two URLs for AI citation-worthiness: side-by-side dimension scores, gap analysis, and prioritized fix recommendations for url_a.
report_saveRender an audit_page / audit_site result as a Markdown report and write it to disk under MCP_WORKSPACE_ROOT.

v0.4.0 renamed tools from flat snake_case to 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 and verification

See the maintenance guide for interpretation limits, current tool names where applicable, and reproducible verification.

Source: README.md at commit f42d4da

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.1LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts