# crawlio-browser

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.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 8
- Author: Crawlio-app
- License: Apache-2.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/Crawlio-app/crawlio-browser
- Updated: 2026-08-10
- HTML: https://affpapa.org/en/nevibecode/mcp/crawlio-browser

## What it 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.

## Requirements
- Needs: Node.js (commands run via npx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add crawlio-browser -- npx -y crawlio-browser
```

### Codex

**Platform CLI**
```bash
codex mcp add crawlio-browser -- npx -y crawlio-browser
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "crawlio-browser": {
            "command": "npx",
            "args": [
                "-y",
                "crawlio-browser"
            ]
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "crawlio-browser": {
            "type": "stdio",
            "command": "npx",
            "args": [
                "-y",
                "crawlio-browser"
            ]
        }
    }
}
```

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add crawlio-browser npx -y crawlio-browser
```

## When to use it
- 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
- 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

## Similar
- [Scrapling MCP Server](https://affpapa.org/en/nevibecode/mcp/scrapling-mcp-server.md) — MCP server · ★ 89433
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119160
- [AIHawk](https://affpapa.org/en/nevibecode/mcp/aihawk.md) — MCP server · ★ 32221
- [Skyvern](https://affpapa.org/en/nevibecode/mcp/skyvern.md) — MCP server · ★ 23263
- [SeleniumBase MCP](https://affpapa.org/en/nevibecode/mcp/seleniumbase-mcp.md) — MCP server · ★ 13169
- [apify-mcp-server](https://affpapa.org/en/nevibecode/mcp/apify-mcp-server.md) — MCP server · ★ 12927

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md