# Page Scanner

> Page Scanner captures a whole web page in the user's own Chrome and writes a PDF whose text stays text, a PNG or JPEG, or Markdown. A Chrome extension does the capture; a command line (`@page-scanner/cli`) and an MCP server (`@page-scanner/mcp`) let an agent drive it on the same machine.

To use it from an agent: the user installs the extension from the Chrome Web Store, then either register the MCP server (`npx -y @page-scanner/mcp serve`) or run the command (`npx @page-scanner/cli`). `install` sets up the helper Chrome starts, and the user presses Connect in the extension's settings once per profile; an agent cannot. Every page below is also plain Markdown at its address with `.md` added. The product's site is https://pagescanner.app.

## Overview

- [Introduction](https://docs.pagescanner.app/index.md): Page Scanner captures a whole web page and keeps its text as text.

## Web extension

- [Getting started](https://docs.pagescanner.app/extension.md): Install the extension and capture your first page.
- [Crop, mark up, zoom and pan](https://docs.pagescanner.app/extension/editor.md): Keep the part of the page worth keeping, draw on it, and move around a capture that may be thousands of pixels tall.
- [Shortcuts](https://docs.pagescanner.app/extension/shortcuts.md): Every key and gesture the editor and the toolbar panel answer to.
- [Export](https://docs.pagescanner.app/extension/export.md): Choose what the file will be in the panels beside the stage, watch the stage show it, then press Extract.
- [A page and its terms in one file](https://docs.pagescanner.app/extension/page-with-terms.md): Capture a checkout page together with the terms it links to, each with its own address and the time, in one PDF or a ZIP of files.
- [Map a site](https://docs.pagescanner.app/extension/site-map.md): Capture up to 30 pages of a site and see them as a flow, each page joined to the pages it links to, ready to open in the editor.
- [Record steps](https://docs.pagescanner.app/extension/record-steps.md): Click through a task once and get a step-by-step guide, a picture and a sentence for each click, with sign-in and ID fields covered, as one PDF.
- [Scan scrolling](https://docs.pagescanner.app/extension/scroll-storyboard.md): Scroll a page once and get its scroll experience as a storyboard, scene by scene, with six frames each and what moved in words, saved as one PDF to hand to an AI coding agent or a person.
- [Settings](https://docs.pagescanner.app/extension/settings.md): The choices that have to be made before a scan, the theme, notifications, the model the AI features ask, the usage statistics and the local agent pairing, in one dialog.
- [Local agents](https://docs.pagescanner.app/extension/local-agents.md): Let a script or an AI agent on your own machine ask the extension for a capture.
- [Why the debugger](https://docs.pagescanner.app/extension/debugger.md): Why a scan attaches Chrome's debugger to the tab, what the "started debugging this browser" bar means, and why it stays a few seconds after the scan.
- [Changelog](https://docs.pagescanner.app/extension/changelog.md): Release notes for the Page Scanner extension, with new features, improvements and bug fixes by version.

## Command line

- [The page-scanner command](https://docs.pagescanner.app/cli.md): Capture a whole web page from a terminal, through the Chrome you already use.
- [Install](https://docs.pagescanner.app/cli/install.md): npx, or a global install.
- [Commands](https://docs.pagescanner.app/cli/commands.md): The whole surface, what each one prints, and what it exits with.
- [Watching a page for changes](https://docs.pagescanner.app/cli/watch.md): A script that scans a page on a schedule, compares it with the last capture, and says so only when it changed.

## MCP server

- [The MCP server](https://docs.pagescanner.app/mcp.md): Nine tools that let a local agent list your tabs, capture one, read a page's design, scan how it scrolls, and check its quotes against the capture.
- [Install](https://docs.pagescanner.app/mcp/install.md): Claude Code, Claude Desktop, Cursor, VS Code, or any client that reads an mcpServers block.
- [Agent skill](https://docs.pagescanner.app/mcp/skill.md): One install teaches Claude Code, Codex, Cursor and the rest when to use Page Scanner and how, and what to say to them.
- [Connecting Chrome](https://docs.pagescanner.app/mcp/pairing.md): One command, then Connect in the extension's settings, once per Chrome profile.
- [Tools](https://docs.pagescanner.app/mcp/tools.md): install, pair, list_browsers, list_tabs, scan_page, diff_captures, extract_design, storyboard_page and check_quotes, with every argument.
- [What an agent can and cannot do](https://docs.pagescanner.app/mcp/security.md): The three checks on every connection, and the honest description of the reach this gives.

## Obsidian plugin

- [Obsidian plugin](https://docs.pagescanner.app/obsidian.md): Save a browser tab into your Obsidian vault as a vector PDF and a Markdown note.

## Raycast extension

- [Raycast extension](https://docs.pagescanner.app/raycast.md): Scan the tab in front of your browser from Raycast, as a vector PDF, a PNG or a JPEG.

## FAQ

- [Frequently asked questions](https://docs.pagescanner.app/faq.md): Short answers about installing, scanning, exporting and connecting agents.