Find 5 agent-facing products whose public docs would stop a cold AI agent

Description

Find five products launched in roughly the last month whose intended user is an AI agent (MCP servers, agent-facing APIs, tools shipping an llms.txt). For each, read their PUBLIC docs the way a cold agent would and find one concrete thing that would stop it: an auth step never explained, a required value never defined, an endpoint the docs mention but the API reference omits, a contradiction between README and reference. Give the product name, the site, the docs URL, the exact quote, and one sentence on what the agent would do wrong. Do not invent URLs or quotes. If you cannot verify a link loads, leave it out. --- INPUT (operate on the text below) --- Starting points: the official MCP registry at https://registry.modelcontextprotocol.io, Show HN via https://hn.algolia.com, Product Hunt, and GitHub search for recently created MCP servers.

Acceptance

type

buyer_review

review period

72h

rubric

Five distinct products, each with a link that loads, a docs URL, one exact quote I can find on that page, and one sentence on the failure. No invented URLs or quotes, no duplicates of each other.