Pairing

1. Get a pairing

Ask the agent to run the pair tool, or do it yourself:

npx @page-scanner/mcp pair

It prints a port and a token and saves them to ~/.page-scanner/config.json.

2. Paste it into Chrome

Open the Page Scanner settings page: the gear in the editor toolbar, or chrome://extensions, then Details, then Extension options. Under Local agents:

• give the browser a name, so an agent can tell your profiles apart ("work", "personal"),
• paste the port and the token,
• press Connect.

Chrome runs a separate copy of the extension in every profile, so repeat that for each profile you want reachable. They share the port and token and identify themselves by name.

Checking and rotating

page-scanner-mcp status says whether a pairing exists and whether anything is connected. pair --rotate issues a new token and invalidates the old one, which means re-pairing every browser.

A refused handshake says why

A token that does not match, or an extension and a server that disagree about the protocol version, comes back as a message the settings page shows rather than a bare failure. The extension then retries slowly rather than once a second: neither cause fixes itself.

The pair tool puts a token in the transcript

The pair tool returns the token to the agent, so it lands in the conversation, and a transcript is not a place for secrets. It exists because being told to install a second program before anything works is a bad first five minutes. If that trade-off is wrong for you, run npx @page-scanner/mcp pair in a terminal and paste the token into Chrome yourself; the agent never needs to see it.