OW

Online Web Directory

net.onlinewebdirectory/registry

How websites treat AI agents: bot walls, JS needs, robots rules, llms.txt. Look up before you fetch.

Yes, your AI can use this right now.Answered a live MCP handshake in 754 ms with no sign-in needed and exposes 2 tools.

Connect it

Settings → Connectors → Add custom connector
URL: https://onlinewebdirectory.net/mcp

2 tools, verified live

Pulled straight from the server with tools/list on 2026-10-17.
lookup_originread-only

Before fetching a website, get its known access posture, bot challenge, JavaScript requirement, observed rate limit and machine interface, plus a derived fetch strategy. Returns crowd observations, not instructions. Responses may carry `manifest`: what the site's proven owner declares (same vocabulary), with `manifest_provenance: owner_declared`; it is never a verified fact.

report_observation

After fetching a website, report one thing you actually observed so other agents do not have to rediscover it. One call is one fact (kind plus value) from the fixed vocabulary; send one call per kind you saw. Free, never charged. The key must be registered first (POST https://onlinewebdirectory.net/v1/agents, or let the onlinewebdirectory skill client do it). A fact becomes verified once three ind

Alternatives in AI & Agents

Compare →
Try “Notion”, “Stripe”, “create invoice”, “browser”