📌Overview

Purpose: To provide an intelligent MCP server that utilizes OpenAI API for advanced code analysis, code collection, and documentation generation.

Overview: MCP Neurolora is a powerful server designed to enhance coding workflows by integrating tools for assessing code quality, collecting and documenting code efficiently. It harnesses the capabilities of OpenAI to deliver insights and improvements for developers.

Key Features:

• Code Analysis: Utilizes OpenAI API to analyze code and provide detailed feedback, including best practices recommendations and GitHub issue generation.

• Code Collection: Gathers code from specified directories into a single markdown file, supporting syntax highlighting and navigation while allowing for pattern-based filtering of files.

---

MCP Neurolora

An intelligent MCP server that provides tools for code analysis using OpenAI API, code collection, and documentation generation.

🚀 Installation Guide

Follow these steps to install MCP Neurolora.

Step 1: Install Node.js

macOS

1. Install Homebrew if not installed:

   /bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"
   

2. Install Node.js 18:

   brew install node@18
   echo 'export PATH="/opt/homebrew/opt/node@18/bin:$PATH"' >> ~/.zshrc
   source ~/.zshrc
   

Windows

1. Download Node.js 18 LTS from https://nodejs.org/
2. Run the installer
3. Open a new terminal to apply changes

Linux (Ubuntu/Debian)

curl -fsSL https://deb.nodesource.com/setup_18.x | sudo -E bash -
sudo apt-get install -y nodejs

Step 2: Install uv and uvx

All Operating Systems

1. Install uv:

   curl -LsSf https://astral.sh/uv/install.sh | sh
   

2. Install uvx:

   uv pip install uvx
   

Step 3: Verify Installation

Run these commands to verify the installation:

node --version  # Should show v18.x.x
npm --version   # Should show 9.x.x or higher
uv --version    # Should show uv installed
uvx --version   # Should show uvx installed

Step 4: Configure MCP Server

Your assistant will help you:

1. Find your Cline settings file, locations include:

   • VSCode macOS: ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
   • Claude Desktop macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
   • VSCode Windows: %APPDATA%/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
   • Claude Windows: %APPDATA%/Claude/claude_desktop_config.json

2. Add this configuration:

   {
     "mcpServers": {
       "aindreyway-mcp-neurolora": {
         "command": "npx",
         "args": ["-y", "@aindreyway/mcp-neurolora@latest"],
         "env": {
           "NODE_OPTIONS": "--max-old-space-size=256",
           "OPENAI_API_KEY": "your_api_key_here"
         }
       }
     }
   }
   

Step 5: Install Base Servers

Ask your assistant: "Please install the base MCP servers for my environment"

Your assistant will:

1. Find your settings file
2. Run the install_base_servers tool
3. Configure all necessary servers automatically

After installation:

1. Close VSCode completely (Cmd+Q on macOS, Alt+F4 on Windows)
2. Reopen VSCode
3. The new servers will be ready to use

Important: A complete restart of VSCode is required after installing the base servers for proper initialization.

This server uses npx for direct npm package execution, optimal for Node.js/TypeScript MCP servers, providing seamless integration with the npm ecosystem.

Base MCP Servers

The following base servers will be automatically installed and configured:

• fetch: Basic HTTP request functionality
• puppeteer: Browser automation for web interaction and testing
• sequential-thinking: Advanced problem-solving tools
• github: GitHub integration features
• git: Git operations support for version control
• shell: Basic shell command execution with commands such as:
  • ls, cat, pwd, grep, wc, touch, find

🎯 What Your Assistant Can Do

Ask your assistant to:

• Analyze code and suggest improvements
• Install base MCP servers for your environment
• Collect code from your project directory
• Create documentation for your codebase
• Generate a markdown file with all your code

🛠 Available Tools

analyze_code

Analyzes code using OpenAI API and generates detailed feedback.

Parameters:

• codePath (required): Path to the code file or directory

Example usage:

{
  "codePath": "/path/to/your/code.ts"
}

The tool will generate:

• Issues and recommendations
• Best practices violations
• Impact analysis
• Steps to fix

Output files:

• LAST_RESPONSE_OPENAI.txt (human-readable analysis)
• LAST_RESPONSE_OPENAI_GITHUB_FORMAT.json (structured data for GitHub issues)

Requires OpenAI API key in environment configuration.

collect_code

Collects code from a directory into a single markdown file with syntax highlighting and navigation.

Parameters:

• directory (required): Directory path to collect code from
• outputPath (optional): Path to save the output markdown file
• ignorePatterns (optional): Array of patterns to ignore

Example usage:

{
  "directory": "/path/to/project/src",
  "outputPath": "/path/to/project/src/FULL_CODE_SRC_2024-12-20.md",
  "ignorePatterns": ["*.log", "temp/", "__pycache__", "*.pyc", ".git"]
}

install_base_servers

Installs base MCP servers to your configuration file.

Parameters:

• configPath (required): Path to MCP settings configuration file

Example usage:

{
  "configPath": "/path/to/cline_mcp_settings.json"
}

🔧 Features

• Code Analysis:
  • OpenAI API integration
  • Structured feedback
  • Best practices recommendations
  • GitHub issues generation
• Code Collection:
  • Directory traversal
  • Syntax highlighting
  • Navigation generation
  • Pattern-based filtering
• Base Server Management:
  • Automatic installation
  • Configuration handling
  • Version management

📄 License

MIT License - feel free to use this in your projects!

👤 Author

Aindreyway

• GitHub: https://github.com/aindreyway

⭐️ Support

Give a ⭐️ if this project helped you!