馃 MoltProbeProbe another site

AI readiness report for amazon.com

amazon.com

Most agents will struggle here.

4 passed 路 6 warnings 路 3 failed

43
GRADE D

Fix these first

  • AI crawlers allowed. robots.txt blocks: GPTBot, OAI-SearchBot, ChatGPT-User, ClaudeBot, Claude-User, PerplexityBot, Google-Extended, CCBot.

  • llms.txt present. No llms.txt at the site root.

  • Structured data (JSON-LD). No JSON-LD (schema.org) on the homepage.

  • Agent skill file (skill.md). No skill.md / skills.md (an instruction file agents can follow).

  • MCP endpoint declared. No MCP manifest (lets agents call your service as a tool).

  • XML sitemap. No sitemap.xml at the root, and none declared in robots.txt.

  • llms-full.txt present. No llms-full.txt (optional, but useful).

  • Machine-readable feed. No RSS/Atom or data feed declared (optional).

  • ai.txt / ai-plugin. No ai.txt or ai-plugin manifest (optional/legacy).

Agent files
32
Crawler access
0
Structured data
57
Content & discovery
76

Agent files

32/100
llms.txt presentFail
No llms.txt at the site root.
Fix: Add a plain text file at /llms.txt with a markdown H1, a one-line summary, and links to your key pages. See llmstxt.org for the format.
llms-full.txt presentWarn
No llms-full.txt (optional, but useful).
Fix: Add /llms-full.txt, the full-text version of your most important content, so LLMs can read it in one file.
Agent skill file (skill.md)Warn
No skill.md / skills.md (an instruction file agents can follow).
Fix: Add /skill.md, a short markdown file that tells an agent what your site does and how to use it.
MCP endpoint declaredWarn
No MCP manifest (lets agents call your service as a tool).
Fix: Run an MCP server and declare it at /.well-known/mcp.json so agents can call your service as a tool.
ai.txt / ai-pluginWarn
No ai.txt or ai-plugin manifest (optional/legacy).
Fix: Optional. Add /ai.txt stating your AI usage policy for crawlers and agents.

Crawler access

0/100
AI crawlers allowedFail
robots.txt blocks: GPTBot, OAI-SearchBot, ChatGPT-User, ClaudeBot, Claude-User, PerplexityBot, Google-Extended, CCBot.
Fix: In robots.txt, allow the AI crawlers. Add groups for GPTBot, ClaudeBot, PerplexityBot and OAI-SearchBot, each with 'Allow: /'.

Structured data

57/100
Structured data (JSON-LD)Fail
No JSON-LD (schema.org) on the homepage.
Fix: Add JSON-LD in a <script type="application/ld+json"> tag, for example an Organization, WebSite or Product schema from schema.org.
Meta descriptionPass
Homepage has a meta description.
OpenGraph tagsPass
Homepage has OpenGraph tags.
Page titlePass
Homepage has a title.

Content & discovery

76/100
XML sitemapWarn
No sitemap.xml at the root, and none declared in robots.txt.
Fix: Publish /sitemap.xml and reference it from robots.txt with a 'Sitemap: https://yoursite.com/sitemap.xml' line.
Content in initial HTMLPass
Initial HTML carries ~478 words of text (agents without JS can read it).
Machine-readable feedWarn
No RSS/Atom or data feed declared (optional).
Fix: Optional. Declare an RSS or Atom feed with <link rel="alternate" type="application/rss+xml">.

Probed 7/30/2026, 5:17:10 PM 路 Free static audit. The paid tier drives a real AI agent through your key tasks to confirm it can actually use your site.

Want this checked every day, not just once?

This probe is a one-time snapshot. We are building the service: every day a real AI agent works through your key tasks, sign up, search, checkout, call your API, and the moment one breaks for agents you get an alert, before your customers' agents run into it. Leave your email and we will reach out when it opens.