A sovereign, local-first MCP server for AI Engine Optimization (AEO), Generative Engine Optimization (GEO), llm.txt auditing, and content stickiness analytics.
Server has 7 tools with basic descriptions and input schemas, but significant quality gaps. Tool names lack action verbs (e.g., 'audit_llm_txt_compliance' vs 'check_llm_txt', 'calculate_geo_ai_readiness_score' is verbose). Descriptions are present but generic (avg ~120 chars, below 194-char baseline). Parameter descriptions are minimal or absent. Output schemas are not documented, tools return JSON strings without declared structure. No error handling guidance, no recovery paths. No tool annotations (readOnlyHint, destructiveHint). Tools are READ_ONLY but this is not formally declared in the schema.
GA4 Analytics Engine: Calculates the 'Retention Gold' Stickiness Score by comparing Average Session Duration against Bounce Rate.
AEO Auditor: Checks for the presence and syntax validity of /llm.txt and /.well-known/llm.txt files on any target domain.
Security Auditor: Verifies RFC 9116 /.well-known/security.txt headers, contact emails, and expiration timestamps.
GEO Engine: Evaluates a webpage's AI-readiness score (0-100) based on schema density, semantic HTML5 tags, and extractable answer blocks.
AEO Snippet Extractor: Scrapes and formats direct-answer snippets optimized for Perplexity, SearchGPT, and Google AI Overviews.
Authority Engine: Queries Tranco domain rank to evaluate domain trust and authority.
No output schemas documented. Tools return JSON strings without declared field structure, forcing LLMs to parse unstructured text. Violates pattern:response-shaper.
Tool names lack action verbs or are overly verbose. 'calculate_geo_ai_readiness_score' (32 chars, p90=27) should be 'score_geo_readiness' or 'get_ai_readiness_score'. Violates pattern:tool naming convention.
No tool annotations (readOnlyHint, destructiveHint, idempotentHint). All tools are READ_ONLY but this is not formally declared in schema, violating current spec alignment (2026-07-28).
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 49 | 2026-07-28+ | v2 |
Schema Auditor: Audits JSON-LD microdata density and identifies missing fields for AI crawlers.
Parameter descriptions are minimal. 'domain_or_url' param has description but lacks format guidance (e.g., 'domain name or full URL; if domain, https:// is prepended'). Violates pattern:constrained-input.
No error recovery guidance. Tools return JSON with 'error' or 'remediation' fields but do not guide LLM on next steps (e.g., 'Try creating an /llm.txt file' vs actionable 'Call create_llm_txt_file() with domain=...'). Violates pattern:recovery-guide.