puch-ai-hack

darshankparmar/puch-ai-hack

3.2

If you are the rightful owner of puch-ai-hack and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

The LinkedIn Profile Reviewer MCP Server is a specialized server designed to enhance LinkedIn profiles using AI-driven analysis and optimization techniques, built for the Puch AI Hackathon 2025.

Tools
2
Resources
0
Prompts
0

LinkedIn Profile Reviewer MCP Server

A Model Context Protocol (MCP) server that extends Puch AI with LinkedIn profile analysis and optimization capabilities. Built for the Puch AI Hackathon 2025.

🚀 Features

  • Profile Analysis: Analyze LinkedIn profile URLs and extract key information
  • Optimization Recommendations: Get AI-powered suggestions to improve profile visibility
  • SEO Analysis: Identify keywords and optimization opportunities
  • Profile Strength Scoring: Receive a comprehensive score and improvement areas
  • Actionable Feedback: Step-by-step guidance for profile enhancement

🛠️ Tech Stack

  • Python 3.8+ with virtual environment
  • FastAPI for the web server
  • MCP Protocol for Puch AI integration
  • BeautifulSoup4 for web scraping
  • Pydantic for data validation

📋 Prerequisites

  • Python 3.8 or higher
  • pip package manager
  • Git (for cloning)

🚀 Quick Start

1. Clone and Setup

git clone <your-repo-url>
cd puch-hackathon

2. Create Virtual Environment

python -m venv venv
# On Windows
venv\Scripts\activate
# On macOS/Linux
source venv/bin/activate

3. Install Dependencies

pip install -r requirements.txt

4. Run the Server

python main.py

The server will start on http://localhost:8000

5. Connect to Puch AI

Use the command in Puch AI chat:

/mcp connect http://localhost:8000/mcp

🔧 Configuration

Create a .env file in the root directory:

MCP_SERVER_NAME=LinkedIn Profile Reviewer
MCP_SERVER_VERSION=1.0.0
MCP_SERVER_DESCRIPTION=AI-powered LinkedIn profile analysis and optimization

📚 API Endpoints

  • GET / - Server status and documentation
  • POST /mcp - MCP protocol endpoint
  • GET /health - Health check endpoint

🎯 MCP Tools

1. analyze_linkedin_profile

Analyzes a LinkedIn profile URL and provides comprehensive feedback.

Parameters:

  • profile_url (string): The LinkedIn profile URL to analyze

Returns:

  • Profile analysis with strengths and weaknesses
  • Optimization recommendations
  • Profile strength score (1-100)
  • Actionable improvement steps

2. validate

Required MCP tool for authentication. Returns the server owner's phone number.

Parameters:

  • bearer_token (string): Authentication token

Returns:

  • Phone number in format: {country_code}{number} (e.g., 919876543210)

🏆 Hackathon Submission

This project is designed for the Puch AI Hackathon 2025. The server:

  • ✅ Implements the required validate tool
  • ✅ Serves over HTTPS (when deployed)
  • ✅ Provides useful LinkedIn profile analysis tools
  • ✅ Follows MCP protocol specifications
  • ✅ Ready for production deployment

🚀 Deployment

Vercel (Recommended)

  1. Install Vercel CLI: npm i -g vercel
  2. Deploy: vercel --prod

Other Platforms

  • Cloudflare Workers
  • Heroku
  • DigitalOcean App Platform
  • AWS Lambda

📊 Usage Tracking

The server includes built-in analytics to track usage for the hackathon leaderboard:

  • Tool usage counts
  • User engagement metrics
  • Performance analytics

🤝 Contributing

  1. Fork the repository
  2. Create a feature branch
  3. Make your changes
  4. Submit a pull request

📄 License

MIT License - see LICENSE file for details

🆘 Support

🎉 Acknowledgments

  • Puch AI team for the MCP protocol implementation
  • RedactAI for inspiration on LinkedIn profile analysis
  • The open-source MCP community

Built with ❤️ for the Puch AI Hackathon 2025