Lcbro MCP
LCBro is a low - cost browser automation MCP server that supports Playwright and Chrome DevTools protocols, provides intelligent data preprocessing and remote browser management functions, and can reduce the cost of calling the LLM API by up to 80%.
2.5 points
7.1K

What is LCBro?

LCBro is a powerful browser automation MCP server specifically designed to optimize the cost of LLM requests. Through intelligent preprocessing and local LLM integration, it cleans and optimizes data before sending it to the expensive main LLM API, saving up to 80% of the cost.

How to use LCBro?

You can use it directly via npx without installation, or install it globally and then start the server. It supports integration with MCP clients such as Claude Desktop and Cursor IDE, providing automation functions such as browser navigation, interaction, and content extraction.

Use cases

Web data scraping, automated testing, content extraction, form filling, login process automation, LLM cost optimization, remote browser management, etc. It is especially suitable for users who need to process a large amount of web data and are concerned about cost optimization.

Main Features

Browser Automation
Supports real browser control, including JavaScript execution, click operations, text input, form processing, screenshot capture, and content extraction, providing session management and persistent context.
Intelligent Preprocessing
Automatically generates preprocessing prompts, integrates local LLMs (Ollama, JAN), performs intelligent content analysis and optimization, and provides cost - effective data preparation.
Multi - Engine Support
Supports both Playwright and Chrome DevTools Protocol (CDP), with automatic detection and fallback mechanisms, and manages remote browser connections.
Advanced Logging System
Comprehensively records LLM interaction logs, tracks performance indicators and tokens, provides configurable log rotation and compression, and has debugging and monitoring functions.
Cost Optimization
Specifically designed to reduce the cost of using LLM, it reduces main API calls through local preprocessing, and performs intelligent content compression and cleaning.
Easy Integration
Can be used without installation, supports mainstream MCP clients, and provides rich configuration options and a command - line interface.
Advantages
Save up to 80% of costs by reducing expensive API calls through intelligent preprocessing.
Can be used without installation, run directly via npx.
Supports multiple browser engines and remote connections.
Has complete automation functions from navigation to content extraction.
Provides detailed logs and performance monitoring.
Seamlessly integrates with mainstream MCP clients.
Limitations
Requires a Node.js 18+ runtime environment.
CDP functions require Chrome/Chromium browsers.
Advanced functions require the configuration of a local LLM service.
A large number of concurrent tasks may require more system resources.

How to Use

Quick Start
Run LCBro directly using npx without installation.
Global Installation
If you need to use it frequently, you can install LCBro globally.
Configure MCP Client
Configure the LCBro server in Claude Desktop or Cursor IDE.
Enable CDP Support
If you need to use Chrome DevTools Protocol functions.
Configure Local LLM
Set up a local LLM service to enable intelligent preprocessing functions.

Usage Examples

Web Content Extraction
Automatically navigate to a web page, extract the main content, and send it to the LLM for analysis after intelligent preprocessing.
Automated Login
Automatically handle the website login process and save the session state for subsequent operations.
Data Table Extraction
Extract table data from a web page and convert it into a structured JSON format.
Cost Optimization Processing
Use the local LLM to preprocess a large amount of web content, reducing the cost of calling the main LLM API.

Frequently Asked Questions

What is LCBro? What makes it special?
How to install and use LCBro?
What is intelligent preprocessing? How does it work?
Which browser engines are supported?
How to configure local LLM integration?
Which MCP clients does LCBro support?
How to enable CDP support?
What is the performance of LCBro?

Related Resources

GitHub Repository
The source code and latest version of LCBro.
npm Package Page
Information and download of the LCBro npm package.
Intelligent Preprocessing Documentation
Details the working principle and configuration of the intelligent preprocessing function.
LLM Logging Guide
How to use and configure the LLM interaction logging system.
CDP Browser Support
Guide to integrating Chrome DevTools Protocol.
Issue Reporting
Submit bug reports and feature requests.
Discussion Area
Discuss usage experiences and best practices with other users.

Installation

Copy the following command to your Client for configuration
{
  "mcpServers": {
    "lcbro": {
      "command": "npx",
      "args": ["-y", "lcbro"]
    }
  }
}

// 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"]
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

R
Rsdoctor
Rsdoctor is a build analysis tool specifically designed for the Rspack ecosystem, fully compatible with webpack. It provides visual build analysis, multi - dimensional performance diagnosis, and intelligent optimization suggestions to help developers improve build efficiency and engineering quality.
TypeScript
8.6K
5 points
N
Next Devtools MCP
The Next.js development tools MCP server provides Next.js development tools and utilities for AI programming assistants such as Claude and Cursor, including runtime diagnostics, development automation, and document access functions.
TypeScript
8.2K
5 points
T
Testkube
Testkube is a test orchestration and execution framework for cloud-native applications, providing a unified platform to define, run, and analyze tests. It supports existing testing tools and Kubernetes infrastructure.
Go
5.1K
5 points
M
MCP Windbg
An MCP server that integrates AI models with WinDbg/CDB for analyzing Windows crash dump files and remote debugging, supporting natural language interaction to execute debugging commands.
Python
9.4K
5 points
R
Runno
Runno is a collection of JavaScript toolkits for securely running code in multiple programming languages in environments such as browsers and Node.js. It achieves sandboxed execution through WebAssembly and WASI, supports languages such as Python, Ruby, JavaScript, SQLite, C/C++, and provides integration methods such as web components and MCP servers.
TypeScript
7.4K
5 points
N
Netdata
Netdata is an open-source real-time infrastructure monitoring platform that provides second-level metric collection, visualization, machine learning-driven anomaly detection, and automated alerts. It can achieve full-stack monitoring without complex configuration.
Go
9.4K
5 points
M
MCP Server
The Mapbox MCP Server is a model context protocol server implemented in Node.js, providing AI applications with access to Mapbox geospatial APIs, including functions such as geocoding, point - of - interest search, route planning, isochrone analysis, and static map generation.
TypeScript
6.7K
4 points
U
Uniprof
Uniprof is a tool that simplifies CPU performance analysis. It supports multiple programming languages and runtimes, does not require code modification or additional dependencies, and can perform one-click performance profiling and hotspot analysis through Docker containers or the host mode.
TypeScript
8.2K
4.5 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
17.7K
4.5 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
30.8K
5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
20.4K
4.3 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
61.4K
4.3 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
26.7K
5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
56.9K
4.5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
19.8K
4.5 points
C
Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
85.4K
4.7 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase