loading…
Search for a command to run...
loading…
AI visibility monitoring. 23 tools for 8 LLM platforms. 19 tools free without API keys.
AI visibility monitoring. 23 tools for 8 LLM platforms. 19 tools free without API keys.
Part of the StudioMeyer MCP Stack — Built in Mallorca 🌴 · ⭐ if you use it
AI visibility monitoring across 8 LLM platforms. 25 MCP tools + 5 expert workflows. Free tier: 20 tools without API keys.
We have been building tools and systems for ourselves for the past two years. The fact that this repo is small and has few stars is not because it is new. It is because we only just decided to share what we have built. It is not a fresh experiment, it is a long story with a recent commit.
We love building things and sharing them. We do not love social media tactics, growth hacks, or chasing stars and followers. So this repo is small. The code is real, it gets used, issues get answered. Judge for yourself.
If it helps you, sharing, testing, and feedback help us. If it could be better, an issue is more useful. If you build something with it, tell us at [email protected]. That genuinely makes our day.
From a small studio in Palma de Mallorca.
StudioMeyer GEO checks how visible your brand is to AI assistants — across ChatGPT, Gemini, Perplexity, Claude, Grok, DeepSeek, Meta AI, and Copilot. Instead of guessing, you get concrete scores, citations, and actionable fixes.
25 expert tools for AI visibility checks, discovery stack audits, robots.txt analysis, JSON-LD validation, entity consistency, sitemap-first content freshness, page-type-aware content audits (KDD 2024 GEO paper), retrieval quality (text-to-HTML ratio + JS dependency + canonical chains), GEO score simulation, citation source analysis, schema generation, hallucination guard for LLM-derived facts, competitor comparison, and historical trend tracking.
20 of 25 tools work without any LLM API key — zero-cost onboarding.
Settings → Connectors → Add URL:
https://geo.studiomeyer.io/mcp
You'll receive a sign-in link via email to verify your identity — no passwords needed.
claude mcp add --transport http geo https://geo.studiomeyer.io/mcp
npx mcp-remote https://geo.studiomeyer.io/mcp
| Tool | Description | API Key |
|---|---|---|
geo_check |
Full GEO check pipeline across 8 LLM platforms | Yes (1+) |
geo_discovery_stack |
llms.txt + agents.json + robots.txt + JSON-LD + sitemap + FAQ schema | No |
geo_calculate_score |
Pure scoring function from raw data | No |
geo_platforms |
LLM platform readiness check (8 platforms) | No |
geo_preview_prompts |
Preview prompts without making API calls | No |
geo_analyze_response |
Parse a single LLM response for brand mentions. Optional hallucination guard (verifyUrls, extractClaims, claimsReference) cross-checks LLM-cited URLs against the real web and tags numeric claims as verified / refuted / unverified. |
No |
geo_recommendations |
Generate actionable recommendations from scores | No |
| Tool | Description | API Key |
|---|---|---|
geo_robots_audit |
Deep robots.txt analysis with 14-AI-bot matrix | No |
geo_llms_txt_validate |
Validate llms.txt against llmstxt.org spec with link checking | No |
geo_json_ld_audit |
Extract and audit JSON-LD structured data | No |
geo_entity_consistency |
Scan for brand name variants. Masks emails, URLs, and bare brand-domain refs before matching, so [email protected] is not counted as a variant. Fragmented entities = 2.8x fewer AI citations. |
No |
geo_content_freshness |
Sitemap-first freshness audit. Reads robots.txt, walks sitemap_index, scores top-N URLs by lastmod + Last-Modified + og:modified_time + schema dateModified. Hardcoded i18n paths only as last-resort fallback. | No |
geo_simulate |
Estimate GEO score without API keys (~30s, free) | No |
geo_schema_generator |
Generate missing JSON-LD blocks ready to paste | No |
geo_citation_sources |
Citability score: authority links, stats, sameAs, quotes | No |
geo_content_audit |
Page-type-aware deep content audit. Detects homepage / blog post / product / local business / about / profile / service / category / contact via JSON-LD @type (with URL-pattern fallback) and applies a tailored weighting profile per type. Based on KDD 2024 GEO paper. |
No |
geo_retrieval_quality |
Static crawler-readiness audit (no headless browser). Text-to-HTML ratio, visible-text length, JS-required markers (DE+EN), <noscript> fallback, meta refresh, canonical mismatch, redirect chain depth via HEAD probe. Score 0..100 + issues. |
No |
geo_dashboard_view |
Interactive visibility dashboard (MCP Apps): score wheel with confidence range, 8-LLM heatmap, citation drift, conversation sankey, recommendations. Renders existing check data. | No |
| Tool | Description | Tier |
|---|---|---|
geo_compare |
Side-by-side GEO comparison of two brands | Free |
geo_brands |
Multi-brand management (list/add/remove/dashboard) | Team |
geo_bulk_check |
Bulk GEO check across all tracked brands | Team |
| Tool | Description | Tier |
|---|---|---|
geo_history |
Past check results with score progression | Pro |
geo_trends |
Score trends: delta, direction, min/max/avg | Pro |
geo_schedule |
Automated checks (daily/weekly/monthly) | Pro |
geo_alerts |
Score-drop / new issues / resolved alerts | Pro |
| Prompt | Use Case |
|---|---|
/geo_full_audit |
Complete chain of all specialists + executive report |
/geo_quick_wins |
API-free checks only, ~30 seconds, quick wins |
/geo_before_launch |
8-point launch checklist with BLOCK/PASS gates |
/geo_competitor_intel |
Discover which brands AI recommends instead of yours |
/geo_track_over_time |
Run check + store results + compare with previous runs |
Six weighted sub-scores:
Rating: 80+ excellent · 65+ good · 40+ needs improvement · 20+ weak · <20 critical
| Feature | Ahrefs Brand Radar | Profound | Peec AI | Otterly | StudioMeyer GEO |
|---|---|---|---|---|---|
| Free tier | — | — | — | — | 20 tools |
| LLM platforms | 6 | 10+ | 4 | 6 | 8 |
| MCP native | — | — | — | — | Yes |
| Discovery Stack depth | — | — | — | — | Yes |
| Fix guidance + schema gen | — | — | Partial | Partial | Yes |
| Content audit (KDD 2024) | — | — | — | — | Yes |
| Citation source analysis | — | — | — | — | Yes |
| Starting price | ~$700/mo | $399/mo | $89/mo | $29/mo | Free |
| Plan | Price | Includes |
|---|---|---|
| Free | €0 | 25 tools, 8 platforms, hosted MCP, OAuth 2.1 |
| Pro | €49/mo (coming soon) | History, trends, scheduled checks, alerts, PDF reports |
| Team | €99/mo (coming soon) | Multi-brand dashboard, agency features, bulk checks |
| Managed Monitoring | €499/mo | Monthly executive report + quarterly strategy call |
| Full GEO Service | €999 + €299/mo | Done-for-you consulting + implementation |
Currently the Free self-service tier and the two managed services (Managed Monitoring, Full GEO Service) are available. The Pro and Team self-service tiers launch shortly — sign up for Free now and you keep your data when they ship.
You: /geo_quick_wins url=https://example.com
Claude runs 10 API-free specialist checks:
✓ robots.txt AI-bot audit (14 bots)
✓ llms.txt validation
✓ JSON-LD structured data audit
✓ Entity consistency scan (with email/URL/domain mask)
✓ Content freshness (sitemap-first)
✓ Page-type-aware content audit
✓ Retrieval quality (text-to-HTML, JS dependency, canonical chain)
✓ Citation source analysis
✓ GEO score simulation
✓ Schema generator (missing blocks)
Result: Estimated score, issues found, prioritized fix list with copy-paste JSON-LD
Connect StudioMeyer Memory to automatically store GEO checks across sessions:
claude mcp add --transport http memory https://memory.studiomeyer.io/mcp
Then use /geo_track_over_time — Claude stores results in Memory and shows trends.
2026-04-13 — v2.0.4 (Benny Windolph Feedback Wave)
Six fixes shipped after detailed feedback from a DACH SEO professional:
detectPageType() (JSON-LD @type first, URL-pattern fallback) plus per-type weighting profile. A homepage isn't judged on expert quotes or author attribution any more.[email protected] false-positive.geo_retrieval_quality specialist — static crawler-readiness audit (no headless browser).geo_analyze_response as opt-in parameters.gpt-5-mini (chatgpt), claude-sonnet-4-5 (claude), gemini-2.5-flash (gemini). The smallest tiers had weaker entity recall and one was silently rejecting calls.StudioMeyer is an AI and design studio based in Palma de Mallorca, working with clients worldwide. We build custom websites and AI infrastructure for small and medium businesses. Production stack on Claude Agent SDK, MCP and n8n, with Sentry, Langfuse and LangGraph for observability and an in-house guard layer.
MIT — see LICENSE. This repository contains documentation only. The GEO server is hosted at geo.studiomeyer.io.
Выполни в терминале:
claude mcp add studiomeyer-geo -- npx Web content fetching and conversion for efficient LLM usage.
Retrieval from AWS Knowledge Base using Bedrock Agent Runtime.
автор: modelcontextprotocolProvides auto-configuration for setting up an MCP server in Spring Boot applications.
A very streamlined mcp client that supports calling and monitoring stdio/sse/streamableHttp, and can also view request responses through the /logs page. It also
автор: xuzexin-hzНе уверен что выбрать?
Найди свой стек за 60 секунд
Автор?
Embed-бейдж для README
Похожее
Все в категории ai