# creavores-aeo-mcp

MCP server for AEO/AI-search audits: direct-answer detection, JSON-LD validation, llms.txt compliance, E-E-A-T signals, agentic-browsing readiness, and AI citation simulation for any URL.

- **Type:** MCP server
- **Trust:** 60/100 (B), scored on the package rubric
- **Verification:** community-indexed — nobody has claimed this listing
- **Version:** 1.0.3
- **Author:** Les Créavores
- **License:** MIT
- **npm:** creavores-aeo-mcp
- **Source:** https://github.com/tresor4k/creavores-aeo-mcp
- **Compatible clients:** claude-code, cursor, copilot, gemini (basis: transport)

## Trust

60/100 (B), scored on the package rubric
- Publisher verified: no
- Install scripts: nothing suspicious found
- Prompt-injection scan: not run
- Obfuscation scan: not run
- Evidence age: 0 days

## Security scan

- **Status:** clean
- **Scanned:** 2026-10-05T01:56:57.582Z
- **Version scanned:** 1.0.3
- **CVEs:** none found by OSV at scan time

## Tools

8 declared. Statically extracted from the shipped source — a floor on the surface, not a census.
- `audit_aeo` — 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
- `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 searc
- `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 (ChatGP
- `check_eeat_signals` — Checks Experience-Expertise-Authoritativeness-Trustworthiness (E-E-A-T) signals on a page: byline/author, publish/modified dates, source citations (external lin
- `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' hea
- `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 
- `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, com
- `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

## Install

**Verdict: review** — Installable, but 1 thing to check first: No publisher has proved control of this listing; it is indexed, not vouched for.
**Cautions** (coverage gaps and advisories — never blocking)
- No publisher has proved control of this listing; it is indexed, not vouched for.
**Config** (claude-code):
```json
"{\n  \"mcpServers\": {\n    \"creavores-aeo\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"creavores-aeo-mcp\"\n      ]\n    }\n  }\n}"
```

## Blast radius

Contained to moderate — no credential declaration found, from the publisher, the upstream registry, or the README. Known so far: runs on your machine; read-only tool surface.
- Floor 13, ceiling 31 (tier: unknown)
- `unknown` means the floor and ceiling land in different bands — not measured enough to name one. It does not mean low.
- This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score.

## Machine-readable views of this entry

- Signed JSON: https://forgeregistry.com/api/v1/packages/creavores-aeo-mcp
- Install plan: https://forgeregistry.com/api/v1/packages/creavores-aeo-mcp/install-plan
- Alternatives: https://forgeregistry.com/api/v1/alternatives/creavores-aeo-mcp
- HTML page: https://forgeregistry.com/registry/creavores-aeo-mcp
- MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan`

## About this document

Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.