Parallel Fetcher
Operated by Parallel
Quick Facts
- User-Agent:
- Shap-User
- Category:
- AI & LLM Bots
- Operator:
- Parallel
- Safety:
- Safe
- Blocking Impact:
- Low - No SEO ranking impact
- SEO Impact Score:
- 2/10
- Official docs:
- None published by Parallel
Reported, not operator documented
Parallel has not published a crawler page that names Shap-User. It is listed here on our own evidence. Verified by AI Crawler Check: 55 of the 5,583 valid robots.txt files in the Tranco top 10,000 carry a rule for Shap-User, 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. Parallel user fetcher; Parallel documents ShapBot and names Shap-User in its crawler docs FAQ.
What that means for you: the Shap-User rule on this page is the best available spelling, but Parallel has made no statement of purpose, crawl rate or robots.txt compliance. Treat a Shap-User 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 Parallel Fetcher?
Parallel Fetcher is an on-demand AI fetcher operated by Parallel. 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 Parallel's assistant.
Parallel Fetcher is an on-demand AI fetcher operated by Parallel. 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 Parallel's assistant.
Parallel Fetcher uses the user-agent token Shap-User. 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 Parallel Fetcher?
User-agent / Disallow: / without any SEO penalty.Want to see whether Parallel Fetcher actually visits you? Read how do I monitor AI bot traffic to my website?
How to block Parallel Fetcher with robots.txt
<code>User-agent: Shap-User</code> - Matching is case-insensitive. Robots.txt is fetched from the root of each subdomain separately.
Is Parallel Fetcher safe to allow?
What does Parallel Fetcher do?
Understanding Parallel Fetcher'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
Parallel Fetcher in context
Parallel Fetcher is a user-triggered agent operated by Parallel. 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 3, mid-priority crawlers with a clear purpose but a smaller audience. 15 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 Parallel Fetcher rests on what you want from Parallel, not on its behaviour. How we rate safety and impact.
How site owners treat Parallel Fetcher
In our own scan of the Tranco top 10,000 (5,583 valid robots.txt files), 55 files (1%) name Shap-User 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?
Parallel Fetcher's operator does not clearly document how it treats robots.txt. Write the Parallel Fetcher rule anyway, then confirm in your logs that its requests stop.
Parallel crawlers and close alternatives
Parallel Fetcher is one of 2 Parallel crawlers in our database. A User-agent: Shap-User group controls Parallel Fetcher only; the other Parallel tokens below need their own lines.
Shap-User: this crawler (Tier 3)ShapBot: Parallel Web Crawler, builds a search or answer index (Tier 3)
To give Parallel Fetcher the same answer as its siblings, stack User-agent: Shap-User with their lines above one set of rules; to treat Parallel Fetcher differently, give it its own group.
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 Parallel Fetcher is usually a decision about the whole group, so check how your file treats these too.
We first recorded Shap-User on September 22, 2026. We could not find a page where Parallel names it, so treat the token as reported rather than documented.
Which rule Parallel Fetcher actually follows
Parallel Fetcher reads exactly one group in robots.txt, the most specific one that names Shap-User, and never combines rules across groups. This short file shows the trap:
User-agent: *
Disallow: /private/
User-agent: Shap-User
Disallow: /drafts/- Find the group. Parallel Fetcher looks for a group naming
Shap-User. One exists, so it ignoresUser-agent: *completely. - Apply only that group. It is refused
/drafts/and nothing else. - The surprise.
/private/is open to Parallel Fetcher, 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 Parallel Fetcher if the file also has a User-agent: Shap-User group?
No. Once a group names it, Parallel Fetcher reads only that group. Put every rule you want it to follow inside its own group.
Test yourself: will blocking Parallel Fetcher remove your pages from AI answers?
Often, yes. Parallel Fetcher 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: shap-user the same as User-agent: Shap-User?
Yes. RFC 9309 makes user-agent matching case-insensitive. Paths are a different story: Disallow: /Blog/ does not block /blog/.
Should you allow Parallel Fetcher? Decide by situation
| If you are... | Recommended setting |
|---|---|
| You publish content and want AI answers to cite it | Allow it. Parallel Fetcher 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 Parallel Fetcher 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 Parallel Fetcher on your own site
- Open
/robots.txton your domain and search forShap-User. If it is not named, it followsUser-agent: *. - List the
Disallowlines in the group Parallel Fetcher 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 Parallel Fetcher even when robots.txt allows it, and that never shows in the file.
- Run our AI search visibility check to see how Parallel Fetcher and every other crawler we track are treated in one pass, including firewall refusals.
Common mistakes with Parallel Fetcher
The errors we see most often with Parallel Fetcher in the files and firewalls we test:
- Assuming a robots.txt rule will stop Parallel Fetcher. 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 Parallel Fetcher 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 Parallel Fetcher 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 Parallel Fetcher from outside after every change.
Spotting Parallel Fetcher in your logs
robots.txt says what Parallel Fetcher 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 "Shap-User" /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 "Shap-User" /var/log/nginx/access.log \
| awk '{print $7}' | sort | uniq -c | sort -rn | head -20Check the requests are genuine
Anyone can send the Parallel Fetcher user-agent, so confirm the source before acting on a match:
Shap-User: we hold no published IP list, so use reverse DNS where the operator documents a hostname and treat an unverifiable Parallel Fetcher request with caution.
Frequently Asked Questions
What user-agent string does Parallel Fetcher use?
Shap-User. Evidence that the spelling is in real use comes from our own robots.txt study: 55 of the 5,583 valid robots.txt files in the Tranco top 10,000 name it (fetched October 20, 2026), not from Parallel, 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 Parallel Fetcher safe?
Will blocking Parallel Fetcher hurt my SEO?
User-agent / Disallow: / without any SEO penalty.How do I block Parallel Fetcher in robots.txt?
/robots.txt file:User-agent: Shap-User Disallow: /
This instructs Parallel Fetcher not to crawl any path on your site. To block only specific sections, replace / with the path (e.g.,
Disallow: /blog/).Does Parallel Fetcher respect robots.txt?
Shap-User will stop a client that chooses to honour it; for enforcement, add a firewall or CDN rule as well.How do I verify if Parallel Fetcher is crawling my site?
Shap-User (for example grep -i "Shap-User" /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 Parallel sent it.