AI Readiness

ai-readiness

Is your website visible to AI search? A tiny, dependency-free CLI that checks whether ChatGPT, Perplexity, Claude, and Google AI can crawl and understand your site, and tells you exactly what to fix.

npx github:epistemedeus/ai-readiness yoursite.com

No install, no signup, no dependencies. Node 18+.

Prefer a browser? Run the same check (no install) at samedaydesk.com/tools/ai-readiness.

📦 Want the fixes done for you? AI Search Readiness Kit: $9

The checker tells you what to fix. This kit gives you everything to fix it, ready to paste:

• Copy-paste robots.txt (welcomes every AI crawler), Organization + WebSite + FAQPage JSON-LD, title/meta/Open Graph templates, and an XML sitemap
• The 7-fix priority checklist in order of impact
• The full benchmark behind the dataset below
• Delivered instantly after checkout, no signup

→ Get the AI Search Readiness Kit ($9) · Prefer a done-for-you audit of your site? See samedaydesk.com.

Dataset: 136 companies scored for AI-search readiness (June 2026)

We ran this checker against the homepages of 136 well-known companies across 7 industries and published the full results. Open data, free to use with attribution.

• Full CSV: data/ai-search-readiness-2026.csv
• Interactive, sortable leaderboard: samedaydesk.com: AI-Search Readiness Leaderboard

Average score by industry (lower = harder for AI search to read):

Notable findings: Healthtech is the least AI-search-ready industry (avg 63). Klarna scored an F (38); GitHub, Chime, Ramp, Gusto, Ro, Hims and Zocdoc each scored a D. Even some AI companies struggle. Perplexity scored a C and LlamaIndex a D. Most gaps are the same and entirely fixable: JavaScript-only homepages, missing JSON-LD structured data, and no sitemap.

Per-industry write-ups: SaaS · e-commerce · marketing agencies · AI startups · healthtech.

Why this matters

AI search is becoming how people find things, and AI answers are pulled from a small set of pages that are crawlable and well-structured. If GPTBot is blocked in your robots.txt, or your pages have no structured data, you can be invisible in AI answers no matter how good your site looks to humans. This tool checks the technical fundamentals that decide whether you're even eligible to be cited.

What it checks

You get a 0-100 score, a letter grade, and a concrete fix for every failing check.

Example

$ npx github:epistemedeus/ai-readiness example.com

AI Readiness  https://example.com/
Score 72/100  Grade B

  PASS  AI crawler access  No AI crawler blocked.
  FAIL  Structured data (JSON-LD)  None found.
        fix: Add Organization + FAQPage + Article JSON-LD.
  PASS  Title & meta description  title 41 chars, description 132 chars
  WARN  Open Graph tags  2 og: tags
        fix: Add og:title, og:description, og:image, og:url.
  PASS  XML sitemap  found
  WARN  llms.txt  none (minor: no proven citation effect)

JSON output for scripting: npx github:epistemedeus/ai-readiness yoursite.com --json

Use as an MCP server

Add the checker to any Model Context Protocol client (Claude Desktop, Cursor, Cline, etc.) so you can ask your AI assistant "is my site visible to AI search?" and get a scored report inline. Dependency-free, runs over stdio.

{
  "mcpServers": {
    "ai-readiness": {
      "command": "npx",
      "args": ["-y", "github:epistemedeus/ai-readiness", "mcp"]
    }
  }
}

It exposes two tools:

• check_ai_readiness(url): returns the score, grade, and a specific fix for each gap.
• generate_ai_readiness_fixes(url): generates starter Organization + FAQPage JSON-LD (pre-filled from the site) and an AI-crawler-friendly robots.txt.

This standalone package is the two-tool local MCP server. Use the npx stdio config above (npx -y github:epistemedeus/ai-readiness mcp, or node mcp.js). http.js is a minimal stateless custom JSON-RPC-over-HTTP POST adapter (POST /mcp); it is not MCP Streamable HTTP, not a production remote MCP transport, and ordinary Streamable HTTP clients cannot use it as-is. There is no hosted remote MCP URL for this package.

Use in CI (GitHub Action)

Fail-fast on AI-search regressions by checking a URL on every deploy:

- uses: epistemedeus/ai-readiness@v1
  with:
    url: https://yoursite.com

The deep version

This CLI checks the technical basics. The questions it can't answer from your markup: do ChatGPT, Perplexity, and Google AI actually cite you for the queries your buyers type? How do you compare to named competitors? What's the highest-ROI fix first?

That's the AI-Search Visibility Audit from SameDayDesk: real citation testing across engines, a competitor benchmark, and a prioritized fix list as a PDF and web report, delivered same day. → samedaydesk.com

Need a custom MCP server?

Like how this one is built: dependency-free, stdio plus a custom JSON-RPC-over-HTTP POST adapter, published to the MCP registry, two focused tools? We build MCP servers for your API or product the same way. (Curious how? Read the guide: How to build a dependency-free MCP server.)

Custom MCP Server: $349, delivered fast. You get a working server (stdio + optional hosted remote), wired to your API, with the registry/manifest setup done. → get one built (or buy directly).

Guides

Free, in-depth guides on getting your site read and cited by AI search:

• How to get cited by ChatGPT, Perplexity & Google AI (2026)
• Why isn't my site showing up in ChatGPT?
• ChatGPT vs Perplexity vs Google AI: which can read your site
• How to add JSON-LD structured data for AI search
• AI crawler list 2026: GPTBot, ClaudeBot, PerplexityBot & how to allow them
• Generative Engine Optimization (GEO) checklist (2026)
• Is llms.txt worth it? We checked the data
• Is your site ready for AI shopping agents?

License

MIT © SameDayDesk