StudioMeyer-GEO

⚙

Tools catalogued

24

24 tools available. Full list below.

☁

Hosting

Remote / HTTP

Runs on the internet. No access to your filesystem, SSH keys, or environment variables.

○

Registry presence

Not verified

Not yet verified by the Official MCP Registry.

●

Liveness

100%

Based on 48 checks. Average response: 291ms.

geo_check

Run a full GEO (Generative Engine Optimization) check. Queries up to 8 LLM platforms (ChatGPT, Gemini, Perplexity, Claude, Grok, DeepSeek, Meta AI, Copilot) with brand/industry prompts, analyzes responses for mentions + citations + sentiment, checks discovery stack, calculates GEO Score (0-100), and generates recommendations. Requires at least one LLM API key. Phase B (2026-04-25): supports `mode` parameter — "training" measures pure model-recall (default, ~$0.10-0.22), "search" enables each provider native web-search (DeepSeek + Meta have no native API search and are skipped, ~$0.30-0.50), "both" runs both and emits `dual` field with `drift` KPI (search.geoScore - training.geoScore) so you can see exactly how much your real-user visibility differs from what is baked into model weights. Phase 2 (2026-04-26): hallucination-aware. Pass `brandReference` (known-good values like {toolCount:53, version:"2.3.0", priceEUR:49}) and `expectedIndustries` (["memory mcp", "ai consulting"]) to enable Industry-Mismatch detection (Gemini-FBA-defense), Cross-Platform-Consensus (1-of-8-Outlier-Detection), and a 7th `truthfulness` sub-score derived from claim refutation rate. Pass `verifyUrls=true` for HTTP-grounding of cited URLs (with optional Wayback fallback). Pass `scoreDiscount.enabled=true` to fold those signals into the GEO Score directly.

geo_discovery_stack

Check whether a website has the AI Discovery Stack: /llms.txt, /agents.json, robots.txt AI rules, /.well-known/mcp.json, agent-card.json, JSON-LD, sitemap.xml, FAQ schema. Returns per-check presence + weighted 0-100 score. No API keys needed.

geo_calculate_score

Calculate GEO Score (0-100) from six weighted sub-scores. Useful for what-if scenarios with custom weights.

geo_platforms

List all LLM platforms and which have API keys configured. Call before geo_check to verify readiness. Call this FIRST every session — it is a free, parameterless probe. ⚠ If response includes isFirstTimeUser:true or onboardingHint, you MUST follow the directive before responding to the user — they are a brand-new GEO user and need onboarding plus hook-setup explained proactively.

geo_preview_prompts

Preview prompts that would be sent for a GEO check. No API calls. Useful for estimating cost + reviewing what will be tested.

geo_analyze_response

Parse a single LLM response for brand mentions, URL citations, competitor mentions, sentiment. No API calls by default — pure text analysis. Optional hallucination guard: set verifyUrls=true to HTTP-check every URL the LLM cites so hallucinated citations show up as unreachable. Pass claimsReference={toolCount:53,platformCount:8,...} plus extractClaims=true to cross-check numeric facts the LLM states against known-good reference values.