# How to make a Claude artifact private · Stacktree

Source: https://stacktr.ee/make-claude-artifact-private

[Skip to content](#main)   [stacktr.ee](/)  [Examples](/#proof) [How it works](/#how) [Pricing](/pricing) [Security](/security) [Log in](https://app.stacktr.ee) [Publish one](https://app.stacktr.ee/?join=1)     By [Steve Smith](/about) · Founder, Stacktree Last updated June 14, 2026          privacy

#  Published Claude artifacts are public. Here is how to make one private.

   Pressing Publish on a Claude artifact creates a public link, and Anthropic's own docs note it may be indexed by search engines. The conversation stays private, but the artifact does not. To keep the same HTML private, host it on a private-by-default URL instead.

  [ Get started free ](https://app.stacktr.ee/?join=1&from=seo_make_claude_artifact_private)   install npx stacktree-install
Copy
     No card · 3 pages free · about a minute

##  Are published Claude artifacts public, and how do you make one private?

Yes. Publishing a Claude artifact creates a public link anyone can open without a Claude account, and Anthropic notes published artifacts may be indexed by search engines. To make one private, leave it unpublished or host the HTML on a private-by-default URL like Stacktree, where the link is unguessable and crawlers are opted out.

## Are published Claude artifacts public?

Yes. Publishing toggles the artifact to public and produces a URL on claude.ai that anyone can open, with no login required. This is the intended behaviour: publish is the share-with-the-world button. What it is not is a private-sharing feature. There is no password, no expiry, and no view analytics in the native flow, and logged-in users can remix a published artifact into their own copy. This covers standard HTML artifacts; AI-powered or Live artifacts that call Claude at runtime still require the viewer to sign in.

One thing that does stay private: the surrounding conversation. Publishing exposes the artifact only, not your chat history or the prompts that produced it. That distinction matters less than it sounds, because the artifact usually carries the data it was built from.

## Do Claude artifacts get indexed by Google?

They can. Anthropic's help documentation on publishing artifacts notes that published artifacts may be indexed by search engines. In practice that means a published artifact is not just reachable by people you sent the link to; it can be crawled, indexed, and surfaced in Google results to anyone searching. An unpublished artifact has no public URL, so it is not indexable.

This is the gap most people miss. "Share via link" feels private because you only sent the link to one person. But a public, indexable URL is discoverable independently of who you shared it with.

## Can people without the link find my Claude artifact?

If it is published, potentially yes. Because the URL is public and may be indexed, someone who never received the link can still land on it through search. If the artifact is unpublished, it stays inside your account and is not reachable. There is no middle "unlisted but uncrawlable" state in the native publish flow, which is the gap a private host fills.

## What is actually exposed

  - The rendered artifact. Public to anyone with the link, and reachable via search if indexed.
 - Whatever the artifact embeds. Agent-generated HTML routinely inlines API responses, customer rows, internal IDs, or prompt context. Publishing the artifact publishes that data too.
 - A remixable copy. Logged-in users can fork a published artifact into their own account.

What is not exposed: your chat history and the conversation around the artifact.

## How to make a Claude artifact private

There are two honest paths.

  - Do not publish it (or unpublish it). An unpublished artifact lives inside your Claude account and is not on a public URL. You can unpublish a version at any time, and per Anthropic's docs, once you unpublish a version you cannot republish that same version. The catch: pages already crawled can linger in search caches until they are re-crawled, so unpublishing is a cleanup, not a guarantee. And an unpublished artifact cannot be opened by someone without a Claude account.
 - Host the HTML privately. Copy the artifact HTML out of Claude (or have Claude Code write it to a file) and publish it to a private-by-default host. The result is a link anyone can open, no Claude account needed, that is not indexed and not discoverable by guessing.

## The private-by-default fix

Stacktree inverts the default. Where Claude publish is public-and-maybe-indexed, Stacktree is private unless you choose otherwise:

  - Unguessable URL. The token is the credential. No directory listing, no public index, nothing to find by guessing.
 - Search and AI opt-out. Every site is served with an X-Robots-Tag opt-out, so even a leaked URL signals crawlers to skip it.
 - Optional gates per link. Add a shared password, an @yourco.com email-domain gate, or an expiry, link by link.
 - Replace-in-place. When the agent revises the artifact it can call update_site with the same slug, so the URL you sent stays valid while the content updates.
 - No Claude account to view. Recipients open a normal link. They do not need a Claude account or a Stacktree account.

If your goal is simply to share an artifact with someone who lacks a Claude account, the step-by-step flow lives on the
[share Claude artifacts](/share-claude-artifacts) page. This page is about the privacy and indexing question specifically: what is public, what gets crawled, and how to keep an artifact off the public web.

##  Claude publish vs. private hosting on Stacktree

     Criterion Claude publish Stacktree     Default visibility  Public link.   Private, unguessable URL.   May be indexed by search engines  Yes, per Anthropic docs.   No, X-Robots-Tag opt-out on every site.   Viewer needs Claude account  No for viewing, yes to remix.   No.   Password gate  No.   Yes, per link.   Email-domain gate  No.   Yes, magic-link verified.   Expiry control  No.   Minutes to years.   Conversation kept private  Yes, artifact only is published.   N/A, no conversation involved.   Zero-setup inside the Claude app  Yes, one button.   Needs a copy or an MCP call.
FAQ

## Frequent questions

     Are published Claude artifacts public? +  Yes. Pressing Publish on a Claude artifact creates a public link that anyone can open without a Claude account. The surrounding conversation stays private, but the artifact itself becomes publicly accessible. There is no password, no expiry, and no view analytics on the native publish flow.   Do Claude artifacts get indexed by Google? +  They can. Anthropic's own help documentation notes that published artifacts may be indexed by search engines, which means a published artifact can appear in Google results and be discovered by people you never sent the link to. An unpublished artifact is not on a public URL and is not indexable.   How do I make a Claude artifact private? +  The native option is to not publish it (or to unpublish it), which keeps it inside your Claude account only. To share the same HTML privately on a real URL, copy the artifact HTML out of Claude and host it on a private-by-default host like Stacktree, which serves it from an unguessable URL with X-Robots-Tag set so it is not indexed, plus optional password or email-domain gates.   Can people without the link find my Claude artifact? +  If the artifact is published, yes in principle: a public URL can be indexed by search engines and surfaced to people who were never sent the link. If it is unpublished, it stays in your account. On Stacktree the answer is no by design: the URL is unguessable, there is no directory listing, and every site is served with an AI/search opt-out header.   Does unpublishing a Claude artifact remove it from Google? +  Unpublishing takes the artifact off its public URL, so new crawls will not find it. But pages that were already indexed can linger in search results and caches until they are re-crawled. The safer pattern is to avoid publishing sensitive artifacts to a public, indexable URL in the first place.   What stays private when I publish a Claude artifact? +  Your chat history and the surrounding conversation are not published, only the artifact itself. But the artifact frequently embeds the data it was built from, like API responses, customer rows, or prompt context, so the artifact being public can still expose real data even though the conversation stays private.   Is Stacktree more private than Claude publish? +  For the artifact itself, yes. Claude publish is public-by-default and search-indexable; Stacktree is private-by-default, with an unguessable URL as the credential, an X-Robots-Tag opt-out on every response, and optional password, email-domain, or expiry gates per link.
Keep reading

## Related guides

   -  [ Share Claude artifacts privately The step-by-step flow for sharing with someone who has no Claude account. ](/share-claude-artifacts)
-  [ Private HTML hosting The four layers of private, from unguessable URL to end-to-end encryption. ](/private-html-hosting)
-  [ Publish from Claude Code Skip the copy/paste, the agent publishes the artifact directly. ](/claude-code)
-  [ The MCP publish tool publish_html, update_site, and delete_site explained end to end. ](/mcp-publish-html)
-  [ Agent-loop hosting Why replace-in-place is the right contract for iterating artifacts. ](/agent-loop-hosting)

References

## Sources and further reading

   -  [ Anthropic, Publishing and sharing artifacts ↗ Anthropic's help article confirming the public link and the search-indexing note. ](https://support.claude.com/en/articles/9547008-publishing-and-sharing-artifacts)
-  [ Anthropic, What are artifacts ↗ Background on what an artifact is and how publishing works. ](https://support.claude.com/en/articles/9487310-what-are-artifacts-and-how-do-i-use-them)
-  [ X-Robots-Tag (Google Search Central) ↗ The header Stacktree sets to opt every site out of search and AI crawls. ](https://developers.google.com/search/docs/crawling-indexing/robots-meta-tag)
-  [ Remove a page from Google (Search Central) ↗ Why an already-indexed page can linger after you unpublish it. ](https://developers.google.com/search/docs/crawling-indexing/remove-information)

##  Keep the artifact, lose the public URL.

 Private by default, not indexed, no Claude account needed to view. Free first publish, no card.

 [
Sign up free →
](https://app.stacktr.ee/?join=1&from=cta_make_claude_artifact_private)   install npx stacktree-install
Copy
         stacktr.ee  [About](/about) [Blog](/blog) [Changelog](/changelog) [Pricing](/pricing) [Security](/security) [FAQ](/faq) [Made with Stacktree](/made-with)  Building with AI agents? See the [developer docs &rarr;](/developers)

---
Full markdown summary of the Stacktree marketing surface: https://stacktr.ee/llms-full.txt
