crawlio-browser — Claude Code MCP server: your live Chrome
Wires your own Chrome into an AI agent through a browser extension and CDP, so the agent sees the tabs, cookies and pages you already have open.
claude mcp add crawlio-browser -- npx -y crawlio-browserWhat crawlio-browser does
crawlio-browser is a Node.js MCP server that hands an agent control of a real Chrome. The client talks to the server over stdio or HTTP, the server keeps a WebSocket to the Chrome extension, and the extension drives the browser through Chrome DevTools Protocol. It ships 150 tools: page capture, data extraction, tracking pixel analysis, technographic fingerprinting, SEO auditing. Static crawlers miss all of it — SPAs, pages behind a login, anything JavaScript renders only shows up in a live browser.
Setup starts with the Chrome extension, then the wizard npx crawlio-browser init detects your client and writes the config. Three modes exist: the default code mode, --full with every tool exposed on its own, and --portal running a persistent HTTP server. For Claude the portal is the recommended pick, since the server survives session restarts and context compaction. You can inspect the surface before configuring anything: npx crawlio-browser tools and npx crawlio-browser doctor run with no browser and no network. The package also builds as an Agent Plugins v1 plugin, but mcp.json starts the server from ${PLUGIN_ROOT}/dist/mcp-server/index.js, so you need the npm-installed copy — an unpacked tarball starts and then dies.
The feature is also the risk. The agent attaches to your Chrome and can act as you on every site where you are signed in, reading cookies, storage and page content for that tab.
What it helps with
- pull data out of an SPA that a plain crawler sees as empty
- walk through pages behind your own login without signing in again
- capture a screenshot and the contents of the open tab
- check a page for tracking pixels and technology fingerprints
- run an SEO audit against the rendered DOM instead of raw HTML
Example prompts for the agent
- Connect the tab with the dashboard and pull the orders table into JSON
- Check this page for tracking pixels and tell me what you find
- Screenshot the current tab and point out what is broken in the layout
How to install crawlio-browser
Platform CLI
claude mcp add crawlio-browser -- npx -y crawlio-browserPlatform CLI
codex mcp add crawlio-browser -- npx -y crawlio-browserConfig file
{
"mcpServers": {
"crawlio-browser": {
"command": "npx",
"args": [
"-y",
"crawlio-browser"
]
}
}
}Config file
{
"servers": {
"crawlio-browser": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"crawlio-browser"
]
}
}
}Platform CLI
gemini mcp add crawlio-browser npx -y crawlio-browserStep by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about crawlio-browser
How do I install crawlio-browser in Claude Code?
Install the Chrome extension first, then run claude mcp add crawlio-browser -- npx -y crawlio-browser. Alternatively run npx crawlio-browser init and let the wizard configure the client.
What does crawlio-browser do?
It gives an agent control of a live Chrome through an extension and CDP, with 150 tools for capture, extraction and page observation.
How is crawlio-browser different from headless browser tools?
Headless tools spawn a separate browser process. Here the agent attaches to your existing Chrome, so your tabs, cookies and sessions are in reach.
