🚀 AI-Powered Job Recommender System with MCP

📌 Overview

The AI-Powered Job Recommender System with MCP (Model Context Protocol) is an intelligent career assistant that helps users discover relevant job opportunities based on their resumes, skills, experience, and career interests.

The system leverages Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and MCP architecture to analyze user profiles, extract key skills, and recommend personalized job opportunities from multiple job platforms.

This project aims to bridge the gap between job seekers and recruiters by providing AI-driven recommendations, resume analysis, and career guidance.

🎯 Features

📄 Resume Analysis

Upload PDF resumes.
Automatically extract text and relevant information.
Identify technical and soft skills.
Analyze education and experience.

🤖 AI-Powered Recommendations

Generate personalized job recommendations.
Match skills with available job roles.
Suggest suitable career paths.
Recommend skill improvements.

🔍 Multi-Platform Job Search

Naukri Job Listings
Future integration with LinkedIn, Indeed, Glassdoor, and Monster

🧠 Generative AI Integration

Uses Groq LLMs for fast inference.
Generates career insights and recommendations.
Provides resume improvement suggestions.

🔗 MCP (Model Context Protocol)

Structured interaction between data sources and AI models.
Context-aware recommendations.
Improved personalization and scalability.

📊 Interactive Dashboard

User-friendly Streamlit interface.
Resume upload functionality.
Job recommendation display.
Job filtering and exploration.

🏗️ System Architecture

User uploads resume.
Resume parser extracts text.
Skills and keywords are identified.
Job APIs fetch relevant openings.
MCP manages contextual information.
Groq LLM analyzes profile and jobs.
Personalized recommendations are generated.
Results are displayed in Streamlit dashboard.

🛠️ Tech Stack

Frontend

Streamlit

Backend

Python

AI & NLP

Groq LLM
Prompt Engineering
Retrieval-Augmented Generation (RAG)

Resume Processing

PyMuPDF (fitz)

Job Data Sources

Apify API
LinkedIn Jobs
Naukri Jobs

Environment Management

Python-dotenv

Version Control

Git
GitHub

📂 Project Structure

AI-Powered-Job-Recommender-System-with-MCP/
│
├── app.py
├── requirements.txt
├── .env.example
│
├── src/
│   ├── job_api.py
│   ├── pdf_parser.py
│   ├── llm_utils.py
│   └── recommendation_engine.py
│
├── assets/
├── data/
├── screenshots/
│
└── README.md

⚙️ Installation

Clone Repository

git clone https://github.com/your-username/AI-Powered-Job-Recommender-System-with-MCP.git

cd AI-Powered-Job-Recommender-System-with-MCP

Create Virtual Environment

python -m venv .venv

Activate Environment

Windows:

.venv\Scripts\activate

Linux/Mac:

source .venv/bin/activate

Install Dependencies

pip install -r requirements.txt

🔑 Environment Variables

Create a .env file:

APIFY_API_TOKEN=your_apify_token
GROQ_API_KEY=your_groq_api_key

▶️ Run Application

streamlit run app.py

Application will be available at:

http://localhost:8501

📸 Screenshots

Add screenshots of:

Home Page
Resume Upload
AI Job Recommendations
Career Insights Dashboard

inside the screenshots/ folder.

🔮 Future Enhancements

ATS Resume Score Analysis
Interview Question Generator
Salary Prediction Module
Job Application Tracker
Skill Gap Analysis
Cover Letter Generator
Email Automation for Applications
Multi-Language Support
Real-Time Job Alerts

🤝 Contributing

Contributions are welcome.

Fork the repository.
Create a new branch.
Commit your changes.
Push the branch.
Create a Pull Request.

⭐ If you found this project useful, please consider giving it a star.

MCP Servers