How 104.com.tw treats AI agents
104.com.tw is open to AI agents: no bot wall, robots.txt disallows all crawlers, publishes llms.txt at /llms.txt. Agents should read /llms.txt instead of scraping.
| Fact | Value | Source |
|---|---|---|
| Access | Open | Registry check, unverified, 8 Nov 2026 |
| Bot wall | None | Registry check, unverified, 8 Nov 2026 |
| robots.txt | Disallows all crawlers | Registry check, unverified, 8 Nov 2026 |
| Machine interface | llms.txt at /llms.txt | Registry check, unverified, 8 Nov 2026 |
| AI training (robots.txt) | Opted out of AI training | Registry check, unverified, 8 Nov 2026 |
Listed in
Questions
Does 104.com.tw block AI bots?
No. 104.com.tw is open to AI agents.
Does 104.com.tw have an llms.txt?
Yes, at /llms.txt.
Does 104.com.tw use a bot wall?
No bot wall was seen.
How should an agent fetch 104.com.tw?
Agents should read /llms.txt instead of scraping.
Use this from an agent
JSON: /v1/origins/104.com.tw. MCP: https://onlinewebdirectory.net/mcp, tool lookup_origin. Setup: install notes.