MCP-Powered AI Job Recommendation Engine

An AI-driven Job Recommendation & Resume Matching Engine integrated with the Model Context Protocol (MCP). This system exposes standardized MCP tools enabling AI agents and assistants (such as Claude, Antigravity, or Custom LLMs) to seamlessly query job recommendations, parse candidate profiles, calculate semantic skill fit scores, and perform automated career matching.

🌟 Key Features

• Model Context Protocol (MCP) Server: Exposes standardized tools (recommend_jobs, match_skills, parse_resume, filter_jobs_by_location).

• Semantic Skill Matching: Utilizes Transformer embeddings and Cosine Similarity to match candidate experience against job descriptions.

• Candidate Skill Gap Analysis: Highlights missing key skills and suggests personalized learning pathways.

• Interactive UI Dashboard: Built with Streamlit for candidate profile uploading and real-time recommendation filtering.

Related MCP server: LinkedIn MCP

🚀 Tech Stack

• Protocol: Model Context Protocol (MCP Python SDK)

• AI & NLP: LangChain, SentenceTransformers, Scikit-Learn, PyTorch

• API & Frontend: FastAPI, Streamlit, Pandas, NumPy

📁 Repository Structure

MCP-Powered-AI-Job-Recommendation-Engine/
├── mcp_server/
│   ├── __init__.py
│   ├── server.py              # MCP Server implementation & tool definitions
│   └── tools.py               # Recommendation tool implementations
├── engine/
│   ├── __init__.py
│   ├── resume_parser.py       # Resume skill extraction engine
│   ├── matcher.py             # Semantic similarity & fit score calculator
│   └── job_database.py        # Job listings & metadata store
├── frontend/
│   ├── app.py                 # Streamlit UI dashboard
├── data/                      # Sample resumes & job description datasets
├── notebooks/                 # Experimentation & embedding evaluation
├── tests/                     # Unit test suites for MCP tools & matcher
├── requirements.txt           # Dependency manifest
└── README.md                  # Project documentation

🛠️ Getting Started

1. Clone the Repository

git clone https://github.com/Devashishpandey1103/MCP-Powered-AI-Job-Recommendation-Engine.git
cd MCP-Powered-AI-Job-Recommendation-Engine

2. Set Up Environment & Install Dependencies

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

pip install -r requirements.txt

3. Run the MCP Server & Web App

# Start the MCP Server (stdio / SSE transport)
python mcp_server/server.py

# Start the Streamlit Dashboard
streamlit run frontend/app.py

Developed as part of Advanced AI Systems & Model Context Protocol Portfolio.