MCP.Market

Créavores AEO Audit MCP server

by tresor4k·io.github.tresor4k/creavores-aeo-mcp·v1.1.0
No reviews yet

AEO audit of any URL + French open data: website prices, public tenders, editorial calendar.

A92/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A92/100

full report

Adoption
Growing

0 stars218 downloads/wk

Reviews

Write one

Nobody has reviewed Créavores AEO Audit yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Créavores AEO Audit tools (11, 1 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • audit_aeowrite action

    Runs a full Answer Engine Optimization (AEO) audit on a URL: crawlability (30pts), content structure for AI extraction (35pts), and E-E-A-T trust signals (35pts), plus llms.txt and AI-bot access checks. Returns a 0-100 score, sub-scores, a verdict, and prioritized, actionable recommendations.

  • check_agentic_readiness

    Assesses how readable and navigable a page is for AI agents performing 'agentic browsing' (Claude, ChatGPT agents, Perplexity, etc.), not just traditional search crawlers. Checks: llms.txt compliance, heading structure sanity, image alt-text coverage, ARIA landmarks/labels, meta robots directives, and whether AI-specific crawlers are blocked in robots.txt. Aligned with Lighthouse's new Agentic Bro

  • check_direct_answer

    Checks whether a page has a concise 40-60 word direct-answer paragraph right under the H1 — the single strongest citability signal for AI/answer engines (ChatGPT, Perplexity, Google AI Overviews). Returns the detected passage, its word count, and a pass/fail verdict.

  • check_eeat_signals

    Checks Experience-Expertise-Authoritativeness-Trustworthiness (E-E-A-T) signals on a page: byline/author, publish/modified dates, source citations (external links), links to an About/Methodology page, and legal-notice/privacy links. These signals matter for YMYL topics and for AI engines assessing whether to trust and cite a source.

  • check_llms_txt

    Checks whether a domain publishes an llms.txt file and whether it follows the llmstxt.org specification: H1 title, optional blockquote summary, '## Section' headings, and Markdown link list items ('- [Title](URL): notes'). Returns existence, a 0-100 compliance score, and the extracted links.

  • compare_aeo

    Compares the AEO scores of 2 to 3 URLs side by side (e.g. your page vs. one or two competitors). Returns each URL's overall score, sub-scores, ranking, and the biggest gaps to close to beat the top-ranked one.

  • extract_structured_data

    Extracts and validates all JSON-LD structured data on a page: parses every <script type="application/ld+json"> block, reports @type list, JSON parse errors, common schema.org mistakes (missing required fields), and confirms the data is present server-side in the raw HTML (not injected client-side via useEffect, which AI crawlers may not execute).

  • get_marches_publics

    Returns live aggregates of French public procurement contracts for websites (DECP open data, plus BOAMP price weighting) from the Les Créavores open dataset: amounts excl. VAT (n, q1, median, q3) per 'category|buyer type' (website creation/redesign, maintenance/hosting, SEO/marketing), number of bids received, yearly breakdown and publication thresholds. Optional filter by buyer type (e.g. commune

  • get_marronniers

    Returns live French editorial calendar dates ('marronniers') for Sept 2026 to Dec 2027 from the Les Créavores open dataset: world days, holidays, school holidays, seasons, public holidays and retail events, each with start/end date, label, type, sectors, source and a content angle. Optional filters: from/to (YYYY-MM-DD, overlap match), sector (also returns dates common to all sectors, 'tous') and

  • get_prix_site

    Returns live French website pricing data from the Les Créavores open dataset (prices publicly displayed by web agencies and freelancers): one cell per 'type|unit' (e.g. 'vitrine|forfait', 'maintenance|mensuel') with sample size n, number of distinct providers and p10/p25/p50/p75/p90 in euros. Optional filters by type and unit; only publishable cells are returned by default. Every answer carries so

  • simulate_ai_citation

    Simulates how an AI answer engine (ChatGPT, Perplexity, AI Overviews) would extract a citable passage from a page. Scans paragraphs, list items, table rows, and FAQ answers, scores each for self-containedness (length, no dangling pronouns, presence of numbers/definitions), and returns the single most citable passage plus an explanation of why it would (or would not) be picked over the others.

Public scan report

scanner v0.1.10 · 2026-10-16 · same rubric, same numbers if you re-run it

no findings
  • Code scan21 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 4 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Créavores AEO Audit compares

Against every graded Productivity MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
92/100
higher than 90% of 1,301 Productivity servers
Tools
11
the typical Productivity server has 7
Tools that change things
9%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
218
more than 72% of 433 Productivity servers with a package

What its tools let an agent do: 10 read · 1 change

Release history: 3 versions in the registry since 2026-09-20, latest 2026-10-12, typically one every 13 days.

Install Créavores AEO Audit in Claude Code, Cursor or VS Code

Runs npx -y creavores-aeo-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add creavores-aeo-mcp -- npx -y creavores-aeo-mcp
Add to Cursor

What the publisher says

From the Créavores AEO Audit repository's README, as published. We do not edit it. Read it on GitHub

creavores-aeo-mcp

An MCP (Model Context Protocol) server that audits any URL for AEO (Answer Engine Optimization) and AI-search readiness — a practical diagnostic tool, not a gadget. It checks the same things ChatGPT, Perplexity, Google AI Overviews, and agentic browsers actually look for: a citable direct answer, valid JSON-LD, llms.txt compliance, E-E-A-T trust signals, and whether AI crawlers/agents can read and navigate the page at all.

Built by Les Créavores, a web & SEO/AEO agency. The scoring logic is compatible with (and extends) the public @macalc/aeo-score package and the free AEO audit tool — scores you get here match what you'd see there.

Installation

No install step needed — run it directly with npx:

npx creavores-aeo-mcp

Claude Desktop

Add to your claudedesktopconfig.json:

{
  "mcpServers": {
    "creavores-aeo": {
      "command": "npx",
      "args": ["-y", "creavores-aeo-mcp"]
    }
  }
}

Claude Code

claude mcp add creavores-aeo -- npx -y creavores-aeo-mcp

Or add it to .mcp.json at the root of your project:

{
  "mcpServers": {
    "creavores-aeo": {
      "command": "npx",
      "args": ["-y", "creavores-aeo-mcp"]
    }
  }
}

No API key, no configuration, no environment variables required. The server fetches pages directly with a self-identifying User-Agent (creavores-aeo-mcp/1.0 (+https://lescreavores.fr)), a 15-second timeout, and never throws — every tool returns clean JSON (including { "error": "..." } on failure) so it's safe to call from any agent loop.

Tools

1. audit_aeo

Full AEO audit: crawlability (30 pts) + content structure for AI extraction (35 pts) + E-E-A-T trust (35 pts), plus llms.txt and AI-bot access checks. Returns a 0-100 score, a verdict, and prioritized recommendations.

{ "url": "https://example.com/pricing" }

→ { score: 78, verdict: "good", subScores: {...}, topRecommendations: [...], issues: [...] }

2. checkdirectanswer

Detects a 40-60 word direct-answer paragraph right under the H1 — the strongest single citability signal for AI engines.

{ "url": "https://example.com/pricing" }

3. extractstructureddata

Extracts and validates every JSON-LD block: types found, parse errors, common schema.org mistakes (missing acceptedAnswer, missing datePublished, etc.), and confirms the data ships server-side (not injected client-side via useEffect, which many AI crawlers never execute).

{ "url": "https://example.com/pricing" }

4. checkllmstxt

Checks existence and llmstxt.org spec compliance: H1 title, blockquote summary, ## Section headings, and Markdown link list items.

{ "domain": "example.com" }

5. checkeeatsignals

Byline/author, publish/modified dates, source citations, About/Methodology page links, legal-notice links, Organization schema.

{ "url": "https://example.com/blog/article" }

6. checkagenticreadiness

Differentiator tool, aligned with Lighthouse's new "Agentic Browsing" audit category: is this page readable and navigable by an AI agent (not just a search crawler)? Checks llms.txt, AI-crawler access in robots.txt, heading hierarchy, image alt-text coverage, ARIA landmarks, viewport meta, and canonical.

{ "url": "https://example.com/app" }

7. simulateaicitation

Simulates how an AI engine would extract a citable passage: scans paragraphs, list items, table rows, and FAQ answers, scores each for self-containedness, and returns the single passage most likely to be quoted — with an explanation of why (or why not).

{ "url": "https://example.com/blog/article" }

8. compare_aeo

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Grade history

  • 2026-10-16restoreC → Ascore 92

Créavores AEO Audit: common questions

Is Créavores AEO Audit MCP server safe?
Yes, by our scan: it is graded A (92/100). Read the Créavores AEO Audit safety report
How do I install Créavores AEO Audit?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Créavores AEO Audit need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Créavores AEO Audit maintained?
The last commit was 24 days ago (2026-10-12). The latest release is v1.1.0.
What can I use instead of Créavores AEO Audit?
Servers from other publishers that do the same job: Agent-Native Calendar MCP server, AIquila — Nextcloud MCP Server and Intervals Icu MCP server.
How does Créavores AEO Audit compare with other Productivity MCP servers?
safety score 92/100 (higher than 90% of 1,301 Productivity servers); tools 11 (the typical Productivity server has 7); tools that change things 9% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Créavores AEO Audit

Same job from other publishers: the closest match first, then the best rated.

  • Agent-Native Calendar
    Agent-Native Google Calendar - manage events, sync, and public booking
    A
  • AIquila — Nextcloud MCP Server
    Nextcloud MCP server — 345 tools: files, calendar, contacts, mail, Talk, Deck, photos, maps, notes
    C
  • Intervals Icu
    Read/write Intervals.icu MCP server: activities, wellness, calendar, gear, and workouts.
    B
  • iCloud MCP
    Apple Mail, Calendar, Contacts, Reminders, Notes, Messages and Safari via AppleScript or iCloud
    B
  • FlutterSDK Docs
    Search Wind UI, Magic, Dusk, Telescope and Artisan documentation. Hosted, public, no auth.
    A

More from tresor4k →