Nyman Media

v0.9

The AI visibility
checkup for your site.

See exactly how AI search engines and other models read your site. Deterministic checks plus a vision-based UX review. First audit is free, no account.

tab to switch

§ how it works

step · 01

Paste a URL

in the audit bar above ↑

Drop any URL in. No signup, no card, no install. First run is free.

step · 02

Get your readiness report

9 sections · pass / warn / fail

Crawlability, structured data, trust signals, content readability for LLMs, and more. Every check ships with observed evidence and a prioritized fix.

step · 03

Gate it on every deploy

$ nmav audit <url> --fail-on-score 70

Same engine ships as a CLI, REST API, and MCP server. Wire it into GitHub Actions, GitLab CI, or any shell. Non-zero exit when your score drops below threshold.

§ what you ship with

audit_sections
9
crawlability · structured data · content · signals · LLM · discoverability · UX · a11y · perf
total_checks
90
pass / warn / fail · each with effort × impact
ux_review
screenshot
visual audit of layout, typography, hierarchy, affordance, forms, and accessibility
industry_benchmark
percentile
see where you rank vs the rest of your industry (sample of top-ranked sites)
monitoring
monthly
auto-rerun, score-over-time, alerts on regressions
export
pdf · csv
branded reports for clients and teams
cli
nmav
`nmav audit <url> --fail-on-score 70` for CI gates · npm i -g @nymanmedia/ai-visibility-cli
mcp_server
/api/mcp
streamable-http MCP endpoint · drives audits from Claude Desktop, Cursor, and other MCP clients

§ what you get

9 Audit Sections

Crawl, content, structured data, trust signals, LLM discoverability, and more.

UX Quality Review

We screenshot your page and grade layout, typography, contrast, and accessibility.

Industry Benchmarks

See where you rank against competitors in your industry.

Monthly Monitoring

Track score changes over time. Get alerts when something regresses.

Prioritized Fixes

Every failing check ships with a specific, actionable fix for your site.

PDF & CSV Export

Branded PDF and CSV exports for clients and teams.

§ developers

Wire it into your stack

Same engine as the web app, exposed as a REST API, a CLI, and an MCP server. Gate deploys on your AI-readiness score in GitHub Actions, GitLab CI, or anywhere that runs npx. Call it from Claude Desktop, Cursor, or any MCP-compatible client.

~/audit · example.com · 63.0s
$ nmav audit example.com→ phase: fetching … 200 OK→ phase: checking · 90 checks across 9 sections→ phase: finalizing
URL: https://example.comScore: 70
[pass] Fetch & URL Integrity (92)[pass] Bot access (78)[warn] Extractability (64)[pass] Structured Data (82)[fail] Trust & Security (65)[warn] Authority (70)
22 findings · report ready in 0.4s(free: 1 audit/day · Premium: 100/day)$

CLI docs · API reference · MCP server · CI/CD recipes

§ faq

What does "AI-ready" mean?+

AI search engines like ChatGPT, Perplexity, and Google AI Overviews crawl, parse, and summarize websites differently than traditional search. An AI-ready site makes its content easy for these systems to discover and accurately represent.

Is the audit really free?+

Yes. No signup needed. Guests get 1 AI readiness audit, 1 UX review, and 1 fix recommendation per day. Sign up free to unlock 3 fix recommendations per day (15/month). Premium gets 100 of each. No credit card to start.

What's included in the UX Quality Review?+

We capture a screenshot of your page and analyze layout, typography, color contrast, mobile-friendliness, and accessibility using computer vision.

How are industry benchmarks calculated?+

We continuously audit top-ranked websites across 20+ industries and compute percentile rankings so you can see where you stand.

Can I audit competitor sites?+

Absolutely. Enter any public URL to audit it, whether it's your own site, a competitor, or any page you're curious about.

Does it work with Claude Desktop, Cursor, or other AI clients?+

Yes. Premium subscribers get an MCP server at /api/mcp that exposes the audit engine as tools. Add it to Claude Desktop, Cursor, or any MCP-compatible client and your AI agent can run audits and check quota directly. See /docs/mcp.