Tavily Search
Operated by Tavily
Quick Facts
- User-Agent:
- TavilyBot
- Category:
- AI & LLM Bots
- Operator:
- Tavily
- Safety:
- Safe
- Blocking Impact:
- Low - No SEO ranking impact
- SEO Impact Score:
- 2/10
- Official docs:
- None published by Tavily
Reported, not operator documented
Tavily has not published a crawler page that names TavilyBot. It is listed here on our own evidence. Verified by AI Crawler Check: 68 of the 5,583 valid robots.txt files in the Tranco top 10,000 carry a rule for TavilyBot, so site owners treat it as a real crawler name (how we measure this). That proves the spelling is in use, not who sends it. Reported Tavily search crawler. No vendor page.
What that means for you: the TavilyBot rule on this page is the best available spelling, but Tavily has made no statement of purpose, crawl rate or robots.txt compliance. Treat a TavilyBot request in your logs as a clue, not proof of who sent it, and add a firewall rule if that traffic matters to you. If the operator publishes documentation, this profile moves to Official docs.
What is Tavily Search?
Tavily Search is an on-demand AI fetcher operated by Tavily. It retrieves a page only when a user explicitly asks an AI assistant or agent to read, summarize, or act on a specific URL. Because it is triggered by real user intent rather than bulk crawling, blocking it mainly prevents users from pulling your content into Tavily's assistant.
Tavily Search is an on-demand AI fetcher operated by Tavily. It retrieves a page only when a user explicitly asks an AI assistant or agent to read, summarize, or act on a specific URL. Because it is triggered by real user intent rather than bulk crawling, blocking it mainly prevents users from pulling your content into Tavily's assistant.
Tavily Search uses the user-agent token TavilyBot. You can control it via robots.txt, meta tags (noai), or the emerging llms.txt standard. Robots.txt is voluntary; for hard enforcement, combine it with server-level IP blocking.
What happens if you block Tavily Search?
User-agent / Disallow: / without any SEO penalty.Want to see whether Tavily Search actually visits you? Read how do I monitor AI bot traffic to my website?
How to block Tavily Search with robots.txt
<code>User-agent: TavilyBot</code> - Matching is case-insensitive. Robots.txt is fetched from the root of each subdomain separately.
Is Tavily Search safe to allow?
What does Tavily Search do?
Understanding Tavily Search's purpose helps you decide whether to allow or block it.
- Fetches a page only when a user asks an AI assistant to read it
- Summarizes or extracts the URL the user provided
- Triggered by real user intent, not bulk crawling
- Low traffic volume compared with training crawlers
- Blocking it prevents users from pulling your content into the assistant
Tavily Search in context
Tavily Search is a user-triggered agent operated by Tavily. In plain terms, it fetches a page when a person asks an assistant or app to open it. Our database files it under AI and LLM crawlers and ranks it Tier 2, important crawlers from established AI and search operators. 74 of the 104 AI and LLM crawlers in our database share this tier.
Its safety rating is safe and its blocking impact is low. So the decision about Tavily Search rests on what you want from Tavily, not on its behaviour. How we rate safety and impact.
How site owners treat Tavily Search
In our own scan of the Tranco top 10,000 (5,583 valid robots.txt files), 68 files (1.2%) name TavilyBot in a User-agent line. That shows site owners treat the token as a real crawler worth a rule. It does not, on its own, prove who operates it.
Does it follow robots.txt?
Tavily Search's operator does not clearly document how it treats robots.txt. Write the Tavily Search rule anyway, then confirm in your logs that its requests stop.
Tavily crawlers and close alternatives
Tavily runs only this one crawler in our database, so a single User-agent: TavilyBot group controls everything Tavily fetches through it.
Other AI and LLM crawlers that do the same job (fetches a page when a person asks an assistant or app to open it) include ChatGPT Agent from OpenAI, ChatGPT Operator from OpenAI, ChatGPT-User from OpenAI, ChatGPT-User/2.0 from OpenAI, Claude-SearchBot from Anthropic, Claude-User from Anthropic. Deciding about Tavily Search is usually a decision about the whole group, so check how your file treats these too.
We first recorded TavilyBot on June 18, 2026. We could not find a page where Tavily names it, so treat the token as reported rather than documented.
Which rule Tavily Search actually follows
Tavily Search reads exactly one group in robots.txt, the most specific one that names TavilyBot, and never combines rules across groups. This short file shows the trap:
User-agent: *
Disallow: /private/
User-agent: TavilyBot
Disallow: /drafts/- Find the group. Tavily Search looks for a group naming
TavilyBot. One exists, so it ignoresUser-agent: *completely. - Apply only that group. It is refused
/drafts/and nothing else. - The surprise.
/private/is open to Tavily Search, because that rule lives in the*group it no longer reads. To keep it out of both, repeatDisallow: /private/inside its own group.
Test yourself: does a rule under User-agent: * apply to Tavily Search if the file also has a User-agent: TavilyBot group?
No. Once a group names it, Tavily Search reads only that group. Put every rule you want it to follow inside its own group.
Related: how AI engines choose their sources
Test yourself: will blocking Tavily Search remove your pages from AI answers?
Often, yes. Tavily Search is a user-triggered agent, so pages it cannot fetch can drop out of the answers or results it supports.
Test yourself: is User-agent: tavilybot the same as User-agent: TavilyBot?
Yes. RFC 9309 makes user-agent matching case-insensitive. Paths are a different story: Disallow: /Blog/ does not block /blog/.
Should you allow Tavily Search? Decide by situation
| If you are... | Recommended setting |
|---|---|
| You publish content and want AI answers to cite it | Allow it. Tavily Search fetches pages for answers, so blocking it can remove you from them. |
| You license content and want to stop AI training | Blocking it does not stop training, because Tavily Search is a user-triggered agent. Block the operator's training crawler instead. |
| You run an online shop | Allow it on product and category pages, which are the pages shoppers ask assistants about. |
| Your server is under load from bots | Rate-limit before blocking. It is rated safe in our database. |
Check Tavily Search on your own site
- Open
/robots.txton your domain and search forTavilyBot. If it is not named, it followsUser-agent: *. - List the
Disallowlines in the group Tavily Search follows and test your key URLs against them; the longest match wins, andAllowwins a tie. - Look beyond the file. A firewall or bot manager can refuse Tavily Search even when robots.txt allows it, and that never shows in the file.
- Run our AI crawler access test to see how Tavily Search and every other crawler we track are treated in one pass, including firewall refusals.
Common mistakes with Tavily Search
The errors we see most often with Tavily Search in the files and firewalls we test:
- Assuming a robots.txt rule will stop Tavily Search. User-triggered fetches act for a person, and some operators say robots.txt may not apply to them. Check the operator's statement above.
- Blocking Tavily Search as if it were a bulk crawler. It fetches one page because a person asked; blocking it means that person's assistant cannot read your page.
- Counting Tavily Search visits as crawl volume. Each request maps to a real user question, which makes the paths it requests a useful signal of what people ask about you.
All three hide inside a file that looks correct, so check Tavily Search from outside after every change.
Spotting Tavily Search in your logs
robots.txt says what Tavily Search may do; your access logs show what it actually did.
Count requests
On a server with standard Nginx or Apache logs, this counts matching requests per day (adjust the log path for your host):
grep -iE "TavilyBot" /var/log/nginx/access.log \
| awk '{print $4}' | cut -d: -f1 | sort | uniq -cAnd this shows which paths it requested most, which is the quickest way to see whether your Disallow lines are being respected:
grep -iE "TavilyBot" /var/log/nginx/access.log \
| awk '{print $7}' | sort | uniq -c | sort -rn | head -20Check the requests are genuine
Anyone can send the Tavily Search user-agent, so confirm the source before acting on a match:
TavilyBot: we hold no published IP list, so use reverse DNS where the operator documents a hostname and treat an unverifiable Tavily Search request with caution.
Frequently Asked Questions
What user-agent string does Tavily Search use?
TavilyBot. Evidence that the spelling is in real use comes from our own robots.txt study: 68 of the 5,583 valid robots.txt files in the Tranco top 10,000 name it (fetched October 20, 2026), not from Tavily, which has not published crawler documentation naming it. Use it in robots.txt as the best available match, and treat a request carrying it as a clue rather than proof of who sent it.Is Tavily Search safe?
Will blocking Tavily Search hurt my SEO?
User-agent / Disallow: / without any SEO penalty.How do I block Tavily Search in robots.txt?
/robots.txt file:User-agent: TavilyBot Disallow: /
This instructs Tavily Search not to crawl any path on your site. To block only specific sections, replace / with the path (e.g.,
Disallow: /blog/).Does Tavily Search respect robots.txt?
TavilyBot will stop a client that chooses to honour it; for enforcement, add a firewall or CDN rule as well.How do I verify if Tavily Search is crawling my site?
TavilyBot (for example grep -i "TavilyBot" /var/log/nginx/access.log). Because the operator publishes no IP ranges or reverse-DNS pattern, a match shows that something used the name, not that Tavily sent it.