Connecting Chrome

1. Set up the helper

Ask the agent to run the install tool (or tell it to set up Page Scanner), or do it yourself:

npx @page-scanner/mcp install

It sets up Page Scanner's helper for every Chromium browser on the computer: Chrome, Chromium, Edge, Brave, Arc, Vivaldi, and Chrome's Beta, Dev and Canary. The helper is the program Chrome starts, through Native Messaging, to connect the extension to the server. Nothing secret comes back, so it is fine for the agent to run.

2. Connect in Chrome

Open the Page Scanner settings: the gear in the editor toolbar (or ⌘/Ctrl + , there), 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"),
• press Connect, and allow Chrome's prompt, which asks whether Page Scanner may "communicate with cooperating native applications" and manage tab groups. The tab groups are for Group an agent's tabs: a page an agent opens sits in a green Page Scanner group while it is scanned. Turn that switch off first if you would rather not allow it.

The first connection can take up to a minute, because Chrome gives the permission to a fresh start of the extension. Leave the settings open, or reload Page Scanner on chrome://extensions to do it at once.

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

Checking

page-scanner-mcp status says whether Page Scanner is set up and whether anything is connected; npx @page-scanner/cli status also says which browsers the helper is set up for. When the extension cannot connect, its settings show a toast saying why, such as a helper that is not set up.

Run install again after installing another browser. npx @page-scanner/cli uninstall takes the helper out of every browser.

With a port and a token instead

The older pairing, for a computer where the helper cannot be installed:

npx @page-scanner/mcp pair

It prints a port and a token and saves them to ~/.page-scanner/config.json. In the settings' Local Agents, set Connect through to A port and a token, paste both, and press Connect. pair --rotate issues a new token and invalidates the old one, which means re-pairing every browser paired this way.

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. Prefer install, which returns none, or run npx @page-scanner/mcp pair in a terminal and paste the token into Chrome yourself.

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.