skip to content
superbot.gg

Screenshot a web page from an agent

Your agent screenshots a page.
It reports what is on it.

Get the app see the real call

What you get

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": "Take a screenshot of https://news.ycombinator.com and tell me the top three story titles."})

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 and two phrases cut: one named a machine, one pointed at an image this page does not carry.

call
superbot({"intent": "Take a screenshot of https://example.com and tell me what it shows."})
reply
Screenshot taken: example.com shows only a plain notice page.

The capture shows a white page with a thin gray border and a small open-book icon at the top. Beneath it is the sentence "This domain is for use in documentation examples without needing permission. This is not a service; avoid relying on it for testing and monitoring purposes."

The same message then repeats in Arabic, Chinese, French, Russian and Spanish, and a single "Learn more" link sits at the bottom, partly cut off at the viewport edge. No header, navigation, images or adverts appear on the page.
A page screenshot, run live. What came back is the agent's description of the capture.

Limits

Needs
A superbot account.
What came back
In the call above, the reply was the agent's description of the capture, in text.
Where it runs
In the browser on your own computer when one is paired, else in a cloud browser.

The page captured is example.com. Read on 2026-10-18.