Crawlio Browser
Connects an AI agent to an existing Chrome tab for browser control, page capture, network inspection, and interaction.
Install Crawlio Browser
Pick your client, then add it in one click or paste the config.
~/Library/Application Support/Claude/claude_desktop_config.json{
"mcpServers": {
"crawlio-browser": {
"command": "npx",
"args": [
"-y",
"crawlio-browser"
]
}
}
}
Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.
Install not yet sandbox-tested— we haven't run this command through our automated sandbox yet. Not a red flag; we're working through the catalog.
Overview
Use cases
- Inspect authenticated web applications using an existing Chrome session
- Capture rendered DOM, console, network, and framework information
- Automate browser interactions such as navigation, form entry, and file uploads
- Test pages under throttled, offline, or intercepted network conditions
- Record screenshots and retrieve response bodies from live pages
Key features
- Live Chrome control through CDP
- Tab connection and status management
- DOM, console, cookie, screenshot, and network inspection
- Framework detection
- Request interception and network emulation
- Stdio, Streamable HTTP, and SSE transport modes
How Crawlio Browser works
Tools80
What Crawlio Browser lets your agent do. Expand a tool for its parameters.
Security & health
What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.
ActiveLast checked 4d ago
Recent health check succeeded.
16/16 checks healthy over the last 67d
Supply-chain signal
No high-severity advisories surfaced by our automated scan.
Critical 0High 0Medium 0Low 0
Scanned 11d ago via OSV.dev · crawlio-browser (npm)
Adoption & maintenance
Factual signals from GitHub, npm, and our automated checks — not a rating.
GitHub stars8Stargazers on the source repository.
npm downloads406Package downloads in the last 30 days.
Last commit2mo agoMost recent push to the default branch.
Tools exposed80Callable tools this server registers over MCP.
Reviews
No reviews yet — be the first to share how it worked for you.
Frequently Asked Questions about Crawlio Browser
crawlio-browser is an MCP server that connects an AI client to a live Chrome tab through a Chrome extension and Chrome DevTools Protocol. Its main tools manage tabs, navigate and interact with pages, capture DOM and network data, read console logs, detect frameworks, take screenshots, and inspect browser state.
Install it by adding the Chrome extension and running `npx crawlio-browser init`. The wizard configures supported MCP clients and can select stdio, full, portal, dry-run, or noninteractive options. You can inspect the configured surface with `npx crawlio-browser tools`.
Yes, crawlio-browser works with Cursor through stdio configuration. The initialization wizard can target Cursor, or you can add an MCP entry that runs `npx -y crawlio-browser` to `.cursor/mcp.json`.
It connects through the Crawlio Chrome extension, which communicates with the Node.js MCP server over WebSocket and controls the selected browser tab through Chrome DevTools Protocol. The agent must connect a tab before browser operations are available.
Yes, it can use the existing logged-in state of the connected Chrome tab, including that session’s page content and browser state. Because the agent can act through the connected session, review the tab first and consider a dedicated Chrome profile.
Related MCP servers
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.
AllMCPs Directory Badge
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
Badge Style:
Live Dynamic SVG Preview
Markdown (GitHub README)
[](https://allmcps.com/mcp/crawlio-browser)HTML Embed
<a href="https://allmcps.com/mcp/crawlio-browser"><img src="https://allmcps.com/api/badge/crawlio-browser?style=directory" alt="Crawlio Browser on AllMCPs" /></a>