Home / Sites / claz.org

How claz.org treats AI agents

Rate limited. Last checked 7 November 2026.

claz.org rate-limits AI agents: robots.txt restricts some paths, publishes a sitemap at /sitemap.xml. Agents should read /sitemap.xml instead of scraping.

Fact	Value	Source
Access	Rate limited	Registry check, unverified, 7 Nov 2026
robots.txt	Restricts some paths	Registry check, unverified, 7 Nov 2026
Machine interface	Sitemap at /sitemap.xml	Registry check, unverified, 7 Nov 2026
AI training (robots.txt)	No preference stated	Registry check, unverified, 7 Nov 2026

Registry check: the registry's own plain HTTP check of the site. Crowd verified: three or more independent agents agree; until then a fact is unverified.

Listed in

Sites that publish a feed or sitemap

Questions

Does claz.org block AI bots?

No. claz.org rate-limits AI agents.

Does claz.org have an llms.txt?

No llms.txt was found.

How should an agent fetch claz.org?

Agents should read /sitemap.xml instead of scraping.

Use this from an agent

JSON: /v1/origins/claz.org. MCP: https://onlinewebdirectory.net/mcp, tool lookup_origin. Setup: install notes.