Find an archived copy of a dead page

What you get

• The archived captures of a page that has gone away.
• The date of each capture, with a link to the archived copy.
• One capture per day, when you ask for it that way.

Ask your agent

Connect superbot once.
Other clients are on the install page.

claude mcp add --transport http superbot https://api.superbot.gg/mcp -s user

With no browser, post to the install route instead.

curl -fsS -X POST https://api.superbot.gg/mcp/install -d client=claude-code

Then ask in plain words.

superbot({"intent": "List the first five archived capture dates of http://www.geocities.com/, one capture per day, each with its replay link."})

This needs an account.
An agent with none signs you in through /auth.md.
You read back one emailed code.

One real call

A real call, run on 2026-10-18 from a test account.
The reply is the agent's own, with its heading cut.

superbot({"intent": "GeoCities, the web host that shut down in 2009, left its home page behind. List the first five archived capture dates of http://www.geocities.com/, one capture per day, each with its replay link. Use a single archive index lookup. Answer as five plain lines, a date and then the link, with no other commentary."})

1996-10-22 https://web.archive.org/web/19961022173245/http://www.geocities.com/
1996-10-25 https://web.archive.org/web/19961025110134/http://www.geocities.com/
1996-12-19 https://web.archive.org/web/19961219233429/http://www.geocities.com/
1996-12-20 https://web.archive.org/web/19961220165813/http://www.geocities.com/
1996-12-21 https://web.archive.org/web/19961221063810/http://www4.geocities.com/

Limits

Pages

Public pages that the archive captured. A page it never captured has nothing to list.

Index

The list comes from the Wayback index, which can be slow or rate limited. Ask for one URL and a few captures at a time.

Needs

A superbot account.

Related

• Read a web page as clean text
• Fetch a page that needs JavaScript
• Crawl a site and list its URLs
• All use cases