Superior Browser MCP

Superior Browser MCP

Enables AI-powered browser automation with real profiles, supporting interaction, navigation, form filling, and advanced features like visual overlays and self-healing selectors.

Category
Visit Server

README

Superior Browser MCP

Browser automation via MCP for Chrome and Firefox with enhanced AI features

npm version License

What is this?

An enhanced MCP (Model Context Protocol) server that surpasses Blueprint MCP with advanced features for AI-powered browser automation. Uses your real browser profile with all your logged-in sessions, cookies, and extensions intact.

Why Superior?

Feature Blueprint MCP Superior Browser MCP
Visual Overlays ❌ ✅ Numbered element badges
Element Classification Basic ✅ Full AI categorization
Form Detection Basic ✅ Smart field matching
Ad Detection ❌ ✅ Auto-detect & block
Popup Handling ❌ ✅ Cookie, modal, notification
Self-Healing Selectors ❌ ✅ Fuzzy matching on failure
Storage Management ❌ ✅ localStorage & sessionStorage
Accessibility Tree Basic ✅ Full ARIA support
CAPTCHA Detection ❌ ✅ Report & alert
Login Form Detection ❌ ✅ Auto-detect credentials
Visual Diff ❌ ✅ Page state comparison

Installation

1. Install the MCP Server

npm install -g @superior/browser-mcp

2. Install the Browser Extension

Chrome / Edge / Opera

  • Download from Releases
  • Load unpacked at chrome://extensions/

Firefox

  • Download from Releases
  • Load at about:debugging#/runtime/this-firefox

3. Configure your MCP client

Claude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "superior-browser": {
      "command": "npx",
      "args": ["@superior/browser-mcp@latest"]
    }
  }
}

Claude Code:

claude mcp add browser npx @superior/browser-mcp@latest

Quick Start

  1. Start your MCP client (Claude Desktop, Cursor, etc)
  2. Click the Superior Browser MCP extension icon in your browser
  3. The extension auto-connects to the MCP server
  4. Ask your AI assistant to browse!

Available Tools

Connection Management

  • enable - Activate browser automation
  • disable - Deactivate browser automation
  • status - Check connection status

Tab Management

  • browser_tabs - List, create, attach, or close tabs

Navigation

  • browser_navigate - Navigate to URL, back, forward, reload

Content & Inspection

  • browser_snapshot - Get accessible page content
  • browser_take_screenshot - Capture visual screenshot
  • browser_extract_content - Extract page as markdown
  • browser_console_messages - Get console logs
  • browser_network_requests - Monitor network

Interaction

  • browser_interact - Click, type, hover, wait, scroll
  • browser_fill_form - Fill multiple form fields
  • browser_press_key - Press keyboard keys
  • browser_drag - Drag and drop elements

Advanced (Blueprint Features)

  • browser_evaluate - Execute JavaScript
  • browser_handle_dialog - Handle dialogs
  • browser_window - Resize, minimize, maximize
  • browser_pdf_save - Save page as PDF
  • browser_performance_metrics - Get Web Vitals
  • browser_verify_text_visible - Verify text
  • browser_verify_element_visible - Verify element

🆕 NEW: Enhanced Features

Visual Overlays

// Get numbered overlays on all interactive elements
get_visual_map({ includeLabels: true })
// Returns: Screenshot with numbered badges + element map

Interactive Element Map

// Get clean JSON map of all interactive elements
get_interactive_map({ 
  filterType: 'button',  // or 'input', 'link', 'form', etc
  filterArea: 'header'    // or 'main', 'footer', 'sidebar'
})

Smart Element Click

// Click element by overlay number from visual map
click_by_overlay_id({ overlayId: 42 })
hover_by_overlay_id({ overlayId: 15 })

Element Classification

analyze_page({
  includeAds: true,      // Detect ad placements
  includePopups: true,   // Detect modals, cookie banners
  includeForms: true,    // Detailed form analysis
  includeNavigation: true,
  includeTables: true
})

Smart Form Filling

smart_fill_form({
  formData: {
    "email": "user@example.com",
    "password": "secret123",
    "name": "John Doe"
  },
  submitAfter: true      // Auto-submit after filling
})

Form Analysis

get_form_analysis({
  includeSuggestions: true  // Get suggested test values
})

Cookie & Storage Management

manage_cookies({ action: 'get' })
manage_cookies({ action: 'set', cookies: [{ name: 'token', value: 'abc123' }] })
manage_cookies({ action: 'delete', name: 'token' })

manage_storage({ action: 'get', type: 'local' })
manage_storage({ action: 'set', type: 'session', key: 'preferences', value: JSON.stringify({ theme: 'dark' }) })

Popup & Ad Detection

detect_popups({ 
  autoClose: true,  // Auto-accept cookies
  types: ['cookie_banner', 'modal', 'notification']
})

detect_ads({ 
  includePositions: true,
  blockAds: true    // Hide detected ads
})

Smart Waiting

wait_for({
  selector: '#dynamic-content',
  visible: true,
  timeout: 10000
})

wait_for({
  text: 'Success message',
  timeout: 5000
})

wait_for({
  condition: 'document.querySelector(".loaded") !== null'
})

Self-Healing Selectors

self_heal_selector({
  failedSelector: '#submit-button',
  textHint: 'Submit',    // Fuzzy match on text
  roleHint: 'button'     // Match by role
})
// Returns: Suggestions for alternative selectors

Accessibility Tree

get_accessibility_tree({
  maxDepth: 10,
  filterRole: 'button'   // Filter by ARIA role
})

CAPTCHA Detection

detect_captcha()
// Returns: { captchaDetected: true/false, type: 'reCAPTCHA', etc }

Login Form Detection

detect_login_form()
// Returns: { loginFormsDetected: true, forms: [...] }

Smart Scrolling

scroll_page({ action: 'lazy_load' })  // Load all lazy content
scroll_page({ action: 'element', selector: '#footer' })
scroll_page({ action: 'bottom' })

How it works

┌─────────────────────────┐
│   AI Assistant          │
│   (Claude, GPT, etc)    │
└───────────┬─────────────┘
            │
            │ MCP Protocol
            ↓
┌─────────────────────────┐
│   MCP Client            │
│   (Claude Desktop, etc) │
└───────────┬─────────────┘
            │ stdio/JSON-RPC
            ↓
┌─────────────────────────┐
│   superior-browser-mcp │
│   (this package)       │
└───────────┬─────────────┘
            │ WebSocket (localhost:5555)
            ↓
┌─────────────────────────┐
│   Browser Extension     │
└───────────┬─────────────┘
            │
            │ Chrome/Firefox APIs
            ↓
┌─────────────────────────┐
│   Your Browser          │
│   (real profile)        │
└─────────────────────────┘

Development

# Clone the repository
git clone https://github.com/superior-browser-mcp/superior-browser-mcp.git
cd superior-browser-mcp

# Install dependencies
npm install

# Run in development
npm run dev

# Build Chrome extension
npm run build:chrome

Project Structure

superior-browser-mcp/
├── server/                     # MCP Server
│   ├── cli.js                  # Server entry point
│   └── src/
│       ├── statefulBackend.js  # All tool implementations
│       ├── extensionServer.js  # WebSocket server
│       └── unifiedBackend.js   # Tool dispatcher
├── extensions/                 # Browser Extensions
│   ├── chrome/                 # Chrome extension (MV3)
│   │   ├── manifest.json
│   │   ├── popup.html
│   │   └── src/
│   │       ├── background.js
│   │       ├── content-script.js
│   │       └── popup.js
│   └── firefox/                # Firefox extension (MV2)
├── docs/                       # Documentation
└── package.json

Configuration

Environment Variables

# Local WebSocket port (default: 5555)
MCP_PORT=5555

# Debug mode
DEBUG=true

Command Line Options

superior-browser-mcp --debug              # Enable verbose logging
superior-browser-mcp --port 8080          # Use custom port

Security

  • MCP server only accepts local connections by default (localhost:5555)
  • Extension requires explicit user action to connect
  • All browser actions go through the browser's permission system

License

Apache License 2.0

Copyright (c) 2025 Superior Browser MCP

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured