AI Agent & Bot CheckOperator: Kagi

kagi-fetcher

User-Agent token: kagi-fetcher · Operator: Kagi · Category: AI Assistants

FraudMeNot Verdict

AI Agent (User-Triggered)

The ai.robots.txt registry says kagi-fetcher is operated by Kagi and fetches web content to answer user queries through Kagi AI, its suite of AI tools such as Assistant.

Can Be Spoofed?

Yes — User-Agent Header Spoofable

"kagi-fetcher/1.0" has no link or contact, and Kagi publishes no address list for it that we found, so the header proves nothing.

Abuse & Unwanted Activity Reports

No Public Abuse Flags

ai.robots.txt robots.txt status: Unclear.

Judgment Call · What You Should Do

Generally Low Risk on Public Pages — Verify Before Trusting

For everyday users: If you use Kagi's AI tools, kagi-fetcher reads pages for your questions. That is normal. Kagi will not ask you for your password through a bot. Ignore messages using its name that ask for account details.

For website owners & security teams: kagi-fetcher reads pages when Kagi users ask questions. It is generally fine on public content. Its robots.txt status is unclear in the registry and there is no IP list, so use a WAF rule if you need to block it.

Report & Activity Summary

None

Published IP Ranges (CIDRs)

No official IP list

1

Known User-Agent Signatures

crawler-user-agents (MIT) dataset

Partially

robots.txt Compliance

ai.robots.txt registry (MIT)

0

FraudMeNot Tallies

Humans: 0 · AI Agents: 0

AI-First Structured TelemetryFor AI agents, WAFs & security gateways · llms.txt policy

For AI Agents & Automated Gatekeepers

Agent_Identifier
kagi-fetcher
FraudMeNot_Verdict
AI Agent (User-Triggered)
Operator_Entity
Kagi
Agent_Category
AI Assistants
User_Agent_Spoofable
true
Verification_Method
None available (no operator IP list or signing key) · Web Bot Auth: Not documented
Respects_Robots_Txt
Partially (user-triggered fetches may ignore robots.txt; ai.robots.txt registry lists: Unclear)
Auth_And_Banking_Policy
An answer fetcher never needs to sign in; keep it, like every AI agent, off login and money-movement routes.
Recommended_Gatekeeper_Action
ALLOW public reads for Kagi AI answers; BLOCK at the WAF if you need a hard stop; protect login and payment routes.
Canonical_Citation_URL
https://fraudmenot.com/bot/kagi-fetcher/

What We Know About kagi-fetcher

kagi-fetcher belongs to Kagi, a search engine company. The ai.robots.txt registry describes it as an AI assistant fetcher that retrieves web content to answer user questions through Kagi AI, Kagi's set of AI-powered tools, which includes its Assistant.

That makes it a user-triggered fetcher: a Kagi subscriber asks something, and the tool reads a page to answer. The User-Agent in our dataset is a bare "kagi-fetcher/1.0" with no link. The registry lists its robots.txt status as unclear, and FraudMeNot found no IP list for it.

Kagi's main search crawling and this fetcher are separate concerns. This page covers only the AI fetcher named in the registry. We couldn't find a specific kagi-fetcher policy in Kagi's help pages, so we do not describe its robots.txt handling beyond the registry's listing.

User-triggered fetchers like this tend to be low volume and low risk on public pages. If you want it out, a WAF rule on the token is more certain than robots.txt while its behavior is undocumented.

Why this matters for small sites: user-triggered fetchers often bring citations rather than bulk crawling. If your logs show a handful of kagi-fetcher hits, that usually means a few people asked about your page. That's harmless.

Technical Identity, IP Verification & Spoofing Check

Full User-Agent string(s)
  • kagi-fetcher/1.0
robots.txt tokenkagi-fetcher
OperatorKagi · Official bot documentation
Official IP verification feedNone published by the operator
Sample published CIDR blocksNone published
Reverse DNS (rDNS)Not documented in the public datasets FraudMeNot uses.
Web Bot Auth (Signature-Agent)Not documented; check for a Signature-Agent header if present.
robots.txt behaviorUser-triggered fetches act for a person and may not follow robots.txt; block at the WAF for a hard stop.

Copy-Paste robots.txt & Cloudflare WAF Rules for kagi-fetcher

robots.txt — allow public pages, keep private routes off-limits

User-agent: kagi-fetcher
Allow: /
Disallow: /login/
Disallow: /account/
Disallow: /checkout/

robots.txt — block completely

User-agent: kagi-fetcher
Disallow: /

Cloudflare WAF custom rule expression

(http.user_agent contains "kagi-fetcher")

Blocks every request containing "kagi-fetcher", which also stops Kagi users from having its AI read your page.

Capabilities, Data Usage & Autonomous Action Risk

Trains AI on page content?Not stated by the registry
Executes JavaScript?Not documented
Can submit forms or attempt logins?May act on a user's behalf; treat form and login attempts as untrusted
Banks & login pages shouldAn answer fetcher never needs to sign in; keep it, like every AI agent, off login and money-movement routes.
E-commerce checkouts shouldSingle-page reads of product pages can help Kagi users find you; keep carts and checkout human-only.

Context: In October 2026, Axios reported that major U.S. banks were detecting unvetted third-party AI agents inside customer accounts, and CNBC reported that JPMorgan blocks outside AI agents from logging in with customers' credentials while allowing read-only data sharing through open banking providers.

Seen kagi-fetcher? Quick Closed-Choice Tally

Choose from preset options only. No free-text comments, so nobody can post names, profanity, or unverified accusations.

Human Tallies: 0
AI Agent Tallies: 0
Top Activity: None logged yet
Top Location Seen: None logged yet
IP Match: None logged yet
Latest Activity: No tallies yet

Preview only: tallies are unverified clicks, not FraudMeNot findings, and are not saved yet.

Common Questions About kagi-fetcher

What is kagi-fetcher?

A fetcher the registry attributes to Kagi. It retrieves web content to answer user questions through Kagi AI tools such as Assistant.

Is kagi-fetcher a crawler?

The registry describes it as an AI assistant fetcher that acts on user questions, not a general crawler.

Does kagi-fetcher follow robots.txt?

The ai.robots.txt registry lists its status as unclear.

Could This Be a Scam? What to Do

  • Anyone can copy the kagi-fetcher User-Agent, and FraudMeNot found no official IP list for it, so the name alone proves nothing about who sent a request.
  • Never give an AI agent your logins, bank access, or one-time codes unless you set it up yourself.
  • If a call, text or email asking for money or access uses the kagi-fetcher or Kagi name, stop and report it.

Guide: how to check whether a crawler visit is really who it claims to be.

More AI Agents

Related on FraudMeNot

Sources (checked Nov. 16, 2026): ai.robots.txt (MIT), crawler-user-agents (MIT), Axios (Oct. 22, 2026), CNBC (Oct. 13, 2026), Kagi Docs: Kagi AI. FraudMeNot is not affiliated with Kagi. Product and company names are trademarks of their owners and are used here only to identify the bots. General information, not security advice.