mcpField
C
Crawlio Browser

Crawlio Browser

Local
github.com/Crawlio-appBrowser Automation2Updated 18w ago
Repository

About Crawlio Browser

Crawlio Browser is a proprietary browser automation agent for AI agents using MCP clients. It provides tools for navigation, page inspection, screenshots, network capture, forms, cookies, tabs, session recording, and structured data extraction through a Chrome extension.

Key features

  1. 01Navigate pages and interact with browser content
  2. 02Capture screenshots and inspect the DOM
  3. 03Capture network traffic
  4. 04Fill forms and manage cookies
  5. 05Orchestrate tabs and record sessions
  6. 06Extract structured data

Use cases

  1. 01Automate navigation and interaction in a browser
  2. 02Inspect page structure and capture screenshots
  3. 03Monitor browser network traffic
  4. 04Extract structured data from web pages

MCP support

Exposes browser automation tools to MCP clients, including Claude, Cursor, VS Code, and Windsurf. The project provides a Chrome extension and can be configured for MCP clients.

#browser-automation#mcp-server#web-scraping#chrome-extension#screenshots#dom-inspection#network-capture#form-filling#ai-tools

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "crawlio-browser-agent": {
      "command": "npx",
      "args": [
        "-y",
        "crawlio-browser"
      ]
    }
  }
}
Run commandnpx -y crawlio-browser

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmcrawlio-browser

Tools

3

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
limitnumberNoMax results (default: 10)
querystringYesSearch keyword (e.g. 'screenshot', 'cookie', 'network', 'navigate')

Details

From the project README

Crawlio Browser Agent

Connect AI to your browser. Navigate, click, screenshot, inspect network traffic, and extract structured data — exposed to any MCP client (Claude, Cursor, VS Code, Windsurf, and more).

ℹ️ This repository hosts distribution and documentation only. Crawlio Browser Agent is proprietary software. The source code is not published here; releases are signed, compiled binaries. See LICENSE.

Install

# npm (recommended — works with any MCP client)
npx -y crawlio-browser init

# Claude Code
claude mcp add crawlio-browser -- npx -y crawlio-browser

# or one-line installer (macOS)
curl -fsSL https://get.crawlio.app/agent | sh

Add to an MCP client config:

{ "mcpServers": { "crawlio-browser": { "command": "npx", "args": ["-y", "crawlio-browser"] } } }

Chrome extension

Install Crawlio for Chrome from the Chrome Web Store: https://www.crawlio.app/browser-agent

Tiers

TierPriceIncludes
Free$0Visible-browser (extension) agent, core tools
Core$59 (one-time)+ headless engine, session vault, basic intelligence
Pro$149 (one-time)+ interceptor, full on-device intelligence

Pricing: https://crawlio.app/pricing

Links

License

Proprietary — © 2026 Crawlio. All rights reserved. See LICENSE.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.