LCBro
Enables browser automation, web content extraction, and LLM-powered data transformation using Playwright. Supports session management, authentication flows, and works with local LLMs (Ollama, JAN AI) or external providers to clean and structure extracted web data.
README
<div align="center"> <br /> <img src="assets/logo.svg" alt="LCBro Logo" width="300" height="225"> <br /> <br />
LCBro
Low Cost Browser Remote Operations
The Cool Browser Automation MCP Server 🔥
<br />
⚡ Lightning Fast • 🎯 Zero Config • 🚀 Production Ready
<br />
</div>
LCBro is a powerful MCP server for browser automation with support for both Playwright and Chrome DevTools Protocol (CDP). It provides intelligent preprocessing, comprehensive logging, and remote browser management capabilities.
✨ Features
<table> <tr> <td width="50%">
🎯 Browser Automation
- Real browser control with JavaScript execution
- Login flows, clicks, text input, form handling
- Screenshot capture and content extraction
- Session management with persistent contexts
🤖 Intelligent Preprocessing
- Auto-generates preprocessing prompts
- Local LLM integration (Ollama, JAN)
- Smart content analysis and optimization
- Cost-efficient data preparation
</td> <td width="50%">
🔧 Multiple Engines
- Playwright: Full-featured automation
- CDP: Chrome DevTools Protocol support
- Remote browser connections
- Auto-detection and fallback
📊 Advanced Logging
- Comprehensive LLM interaction logs
- Performance metrics and token tracking
- Configurable log rotation and compression
- Debug and monitoring capabilities
</td> </tr> </table>
🚀 Quick Start
Use with npx (Recommended - No Installation)
# Use directly without installation
npx lcbro
# With custom configuration
npx lcbro --config /path/to/config.yaml --port 3000
Global Installation
# Install globally via npm
npm install -g lcbro
# Start the server
lcbro
Local Development
# Clone and install
git clone https://github.com/lcbro/lcbro.git
cd lcbro
npm install
npm run build
npm start
Docker
# Run with Docker
docker run -p 3000:3000 lcbro:latest
💡 Usage Examples
Basic Browser Automation
# Navigate and extract content
npx lcbro navigate --url "https://example.com"
npx lcbro extract --format text
With Custom Configuration
# Enable CDP support
npx lcbro --cdp-enabled --port 3001
# Custom logging directory
npx lcbro --logs-dir "/custom/logs" --log-level debug
MCP Client Integration
{
"mcpServers": {
"lcbro": {
"command": "npx",
"args": ["-y", "lcbro"]
}
}
}
📋 Installation
Prerequisites
- Node.js 18+
- npm or yarn
- Chrome/Chromium browser (for CDP support)
Global Installation (Recommended)
# Install globally
npm install -g lcbro
# Verify installation
lcbro --version
Local Development
# Clone repository
git clone https://github.com/lcbro/lcbro.git
cd lcbro
# Install dependencies
npm install
# Build project
npm run build
# Install Playwright browsers
npm run install:browsers
⚙️ Configuration
LCBro uses YAML configuration files with CLI overrides. Create a config/default.yaml file or use CLI options:
Basic Configuration
server:
host: "localhost"
port: 3000
browser:
engine: playwright # playwright | cdp
headless: true
defaultTimeoutMs: 30000
maxContexts: 8
storageDir: /data/profiles
llm:
defaultModel: "ollama:llama3.1"
maxOutputTokens: 2000
temperature: 0
host: "localhost"
port: 11434
janPort: 1337
autoPreprocess: true
security:
allowDomains: ["example.com", "gov.br"]
blockPrivateNetworks: true
CLI Configuration Overrides
# Server settings
lcbro --port 3001 --host 0.0.0.0
# CDP browser support
lcbro --cdp-enabled --cdp-port 9222
# Remote CDP server
lcbro --remote-url https://cdp.example.com:9222 --remote-ssl-mode enabled
# Logging configuration
lcbro --log-level debug --logs-dir /tmp/lcbro-logs
🖥️ CLI Usage
LCBro provides a comprehensive command-line interface:
Main Commands
# Start the server
lcbro
# Show help
lcbro --help
# Show current configuration
lcbro config
# Launch browsers with CDP
lcbro browser:launch -b chrome -p 9222
# Manage log files
lcbro logs --command summary
# Test remote CDP connection
lcbro test:remote -u https://cdp.example.com:9222
🔧 Environment Variables
LCBro supports configuration via environment variables:
LLM Configuration
# Local LLMs (Recommended)
#### Ollama (free, no API keys required)
```bash
# Install Ollama
curl -fsSL https://ollama.ai/install.sh | sh
# Pull a model
ollama pull llama3.1
# Configure LCBro
export LLM_HOST=localhost
export LLM_PORT=11434
export LLM_DEFAULT_MODEL=ollama:llama3.1
JAN AI (free, with optional API key)
# Configure LCBro for JAN AI
export LLM_HOST=localhost
export LLM_JAN_PORT=1337
export LLM_DEFAULT_MODEL=jan:llama-3.1-8b
External LLM APIs (Optional)
# OpenAI
export OPENAI_API_KEY=your_api_key_here
# Anthropic
export ANTHROPIC_API_KEY=your_api_key_here
CDP Browser Configuration
# Enable CDP support
export BROWSER_ENGINE=cdp
# CDP server settings
export CDP_HOST=localhost
export CDP_PORT=9222
# Remote CDP server
export CDP_REMOTE_URL=https://cdp.example.com:9222
export CDP_REMOTE_SSL_MODE=enabled
export CDP_REMOTE_API_KEY=your_api_key
## 🚀 Usage
### Starting the Server
```bash
# Start with default configuration
lcbro
# Start with specific port
lcbro --port 3001
# Start with CDP support
lcbro --cdp-enabled
# Start with custom config file
lcbro --config /path/to/config.yaml
MCP Client Integration
# Claude Desktop configuration
# Add to ~/.claude/claude_desktop_config.json:
{
"mcpServers": {
"lcbro": {
"command": "npx",
"args": ["-y", "lcbro"]
}
}
}
# Cursor IDE configuration
# Add to ~/.cursor/mcp.json:
{
"mcpServers": {
"lcbro": {
"command": "npx",
"args": ["-y", "lcbro"]
}
}
}
# With CDP support
{
"mcpServers": {
"lcbro": {
"command": "npx",
"args": ["-y", "lcbro", "--cdp-enabled"]
}
}
}
# With custom configuration
{
"mcpServers": {
"lcbro": {
"command": "npx",
"args": ["-y", "lcbro", "--config", "/path/to/config.yaml"]
}
}
}
## 🛠️ Advanced Features
### Intelligent Preprocessing
LCBro automatically cleans and optimizes data before sending to LLMs:
```bash
# Enable intelligent preprocessing
lcbro --auto-preprocess
# Configure preprocessing thresholds
lcbro --preprocessing-threshold-html 5000
lcbro --preprocessing-threshold-text 8000
CDP Browser Management
# Launch browsers with CDP
lcbro browser:launch -b chrome -p 9222 -n 3
# Connect to remote CDP server
lcbro --remote-url https://cdp.example.com:9222
# Test remote connection
lcbro test:remote -u https://cdp.example.com:9222
Log Management
# View log summary
lcbro logs --command summary
# Clean old logs
lcbro logs --command cleanup --age 30
# Compress log files
lcbro logs --command compress
📚 Documentation
- Intelligent Preprocessing - Automatic data cleaning and optimization
- LLM Logging Guide - Comprehensive logging system
- CDP Browser Support - Chrome DevTools Protocol integration
- Remote CDP Support - Remote browser management
- Logs Directory Configuration - Log management setup
🎯 MCP Tools Available
LCBro provides the following MCP tools:
Navigation Tools
navigate_open- Open a new URL in a browser contextnavigate_goto- Navigate to a URL in an existing context
Interaction Tools
interact_click- Click on elements by selector, text, or roleinteract_type- Type text into input fieldsinteract_wait- Wait for conditions (selector, network idle, URL change)
Extraction Tools
extract_content- Extract page content in various formatsextract_table- Extract table data as JSONextract_attributes- Extract attributes from elementsextract_screenshot- Take screenshots of pages or elements
Session Tools
session_auth- Perform authentication sequencessession_manage- Manage browser sessions and contexts
LLM Tools
llm_transform- Transform data using LLM with custom instructionsllm_analyze- Analyze content with LLM preprocessing
🏆 Project Status
✅ Production Ready - All features implemented and tested
✅ npm Package Ready - Can be installed globally via npm
✅ CLI Interface - Full command-line interface available
✅ Documentation - Comprehensive documentation provided
✅ Multi-language Support - English, Russian, Portuguese
✅ Zero Breaking Changes - All original functionality preserved
✅ Continuous Integration - Automated testing and deployment
✅ Docker Support - Multi-stage builds and container testing
✅ Security Scanning - Automated vulnerability detection
🚀 Quick Start
Option 1: Use with npx (Recommended - No Installation Required)
# Use directly without installation
npx lcbro --help
# Start server
npx lcbro
# With CDP support
npx lcbro --cdp-enabled
Option 2: Global Installation
# Install globally
npm install -g lcbro
# Verify installation
lcbro --version
# Start server
lcbro
Configure MCP Client
// Claude Desktop: ~/.claude/claude_desktop_config.json
{
"mcpServers": {
"lcbro": {
"command": "npx",
"args": ["-y", "lcbro"]
}
}
}
// Cursor IDE: ~/.cursor/mcp.json
{
"mcpServers": {
"lcbro": {
"command": "npx",
"args": ["-y", "lcbro"]
}
}
}
📊 Performance & Specifications
- Package Size: 147.7 kB compressed, 759.7 kB unpacked
- Startup Time: < 2 seconds
- Memory Usage: < 100 MB typical
- Concurrent Sessions: Up to 8 browser contexts
- Supported Browsers: Chrome, Chromium, Edge (CDP), Playwright browsers
- Node.js: 18.x, 20.x, 22.x
- Operating Systems: Windows, macOS, Linux
🔧 CI/CD Pipeline Status
Automated Testing & Deployment 🚀
📊 Quality Metrics
- Test Coverage: >80% (Unit + E2E)
- Build Time: ~3-5 minutes
- Docker Build: Multi-stage with layer caching
- Security: CodeQL analysis + dependency scanning
📋 View all workflows → | 🚀 View pipeline runs →
🛠️ Development
Prerequisites
npm install
npm run install:browsers
Build & Test
# Build the project
npm run build
# Run tests
npm test
# Run E2E tests
npm run test:e2e
# Run CI pipeline locally
make ci
📄 License
This project is licensed under the MIT License - see the LICENSE file for details.
🤝 Contributing
- Fork the repository
- Create a feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'Add amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
📞 Support & Community
<div align="center">
</div>
- 🐛 Bug Reports: GitHub Issues
- 💬 Discussions: GitHub Discussions
- 📚 Documentation: Full Documentation
- 💡 Examples: Usage Examples
- 🔧 CI/CD Workflows: Workflows Documentation
- 🚀 Pipeline Status: GitHub Actions
- 🛡️ Security Reports: Security Tab
- ⭐ Star Us: Help us grow by starring the repository!
🙏 Acknowledgments
- Playwright - Browser automation framework
- Chrome DevTools Protocol - Remote browser debugging
- MCP SDK - Model Context Protocol framework
- Claude Desktop - MCP client integration
- Cursor IDE - Development environment
<div align="center">
Made with ❤️ by the LCBro Team
LCBro - Low Cost Browser Remote Operations
Version: 1.0.10 • Status: ✅ Production Ready • License: MIT
</div>
Recommended Servers
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.
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.
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.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
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.
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.