💼 Job Matching

AI-powered resume analysis & job discovery — Streamlit UI + MCP server

Upload a PDF resume, get instant AI insights, and pull live listings from LinkedIn and Naukri — all in one place.

Features · Quick Start · Usage · MCP Server · Project Structure

---

✨ Features

Capability	Description
📄 Resume parsing	Extracts text from uploaded PDF resumes via PyMuPDF
🧠 AI analysis	GPT-4o summarizes skills, experience, and education
🔍 Skill gap detection	Identifies missing skills and suggests improvements
🗺️ Career roadmap	Generates a personalized preparation strategy
🎯 Smart job search	Derives search keywords from your resume automatically
💼 LinkedIn jobs	Fetches live listings through Apify actors
🇮🇳 Naukri jobs	Pulls India-focused roles from Naukri.com
🔌 MCP integration	Exposes job-fetch tools for AI agents (Cursor, Claude Desktop, etc.)

---

🏗️ Architecture

flowchart TB
    subgraph UI["Streamlit App (app.py)"]
        A[Upload PDF Resume] --> B[Extract Text]
        B --> C[GPT-4o Analysis]
        C --> D[Summary · Skill Gaps · Roadmap]
        D --> E[Generate Search Keywords]
        E --> F[Fetch Jobs]
    end

    subgraph MCP["MCP Server (mcp_server.py)"]
        G[get_linkedin_jobs]
        H[get_naukri_jobs]
    end

    subgraph External["External Services"]
        I[(OpenAI API)]
        J[(Apify — LinkedIn Actor)]
        K[(Apify — Naukri Actor)]
    end

    B --> I
    C --> I
    D --> I
    E --> I
    F --> J
    F --> K
    G --> J
    H --> K

    style UI fill:#1E1E2E,stroke:#FF4B4B,color:#fff
    style MCP fill:#1E1E2E,stroke:#FFD700,color:#fff
    style External fill:#1E1E2E,stroke:#97D700,color:#fff

Loading

---

📋 Prerequisites

Before you begin, make sure you have:

• Python 3.13+ (.python-version is set to 3.13)
• An OpenAI API key — used for resume analysis
• An Apify API token — used for LinkedIn & Naukri job scraping
• uv (recommended) or pip for dependency management

---

🚀 Quick Start

1. Clone & enter the project

git clone <your-repo-url>
cd job-matching

2. Install dependencies

Option A — uv (recommended)

uv sync

Option B — pip

python -m venv .venv
source .venv/bin/activate   # Windows: .venv\Scripts\activate
pip install -r requirements.txt

3. Configure environment variables

Create a .env file in the project root:

OPENAI_API_KEY=sk-your-openai-key-here
APIFY_API_KEY=apify_api_your-token-here

⚠️ Never commit .env to version control. It is already listed in .gitignore.

4. Run the Streamlit app

uv run streamlit run app.py
# or
streamlit run app.py

Open http://localhost:8501 in your browser, upload a PDF resume, and follow the on-screen flow.

---

📖 Usage

Streamlit workflow

1. Upload your resume (PDF only)
2. Wait for AI processing:
   • Resume summary
   • Skill gaps & missing areas
   • Future roadmap & preparation strategy
3. Click Get Job Recommendations to:
   • Auto-extract search keywords from your profile
   • Fetch up to 60 jobs each from LinkedIn and Naukri
4. Browse results with direct links to apply

What the AI generates

Section	Prompt focus
Resume Summary	Skills, experience, and education highlights
Skill Gaps	Missing skills and improvement suggestions
Future Roadmap	Career preparation strategy tailored to your profile
Job Keywords	Comma-separated titles/keywords for job board search

---

🔌 MCP Server

The project includes an MCP (Model Context Protocol) server so AI assistants can fetch jobs programmatically.

Available tools

Tool	Parameters	Returns
get_linkedin_jobs	search_query, location (default: "india"), rows (default: 60)	List of LinkedIn job dicts
get_naukri_jobs	search_query, location (default: "india"), rows (default: 60)	List of Naukri job dicts

Run the MCP server

uv run python mcp_server.py
# or
python mcp_server.py

The server uses stdio transport by default.

Connect in Cursor

Add this to your Cursor MCP settings (.cursor/mcp.json or Settings → MCP):

{
  "mcpServers": {
    "job-matching": {
      "command": "uv",
      "args": ["run", "python", "mcp_server.py"],
      "cwd": "/absolute/path/to/job-matching",
      "env": {
        "APIFY_API_KEY": "your-apify-key"
      }
    }
  }
}

Connect in Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS):

{
  "mcpServers": {
    "job-matching": {
      "command": "uv",
      "args": ["run", "python", "mcp_server.py"],
      "cwd": "/absolute/path/to/job-matching"
    }
  }
}

---

📁 Project Structure

job-matching/
├── app.py                 # Streamlit web application
├── mcp_server.py          # MCP server (stdio transport)
├── pyproject.toml         # Project metadata & dependencies (uv)
├── requirements.txt       # Pip-compatible dependency list
├── uv.lock                # Locked dependency versions
├── .env                   # API keys (local only — not committed)
├── .python-version        # Python version pin (3.13)
└── src/
    ├── helper.py          # PDF extraction & OpenAI chat helper
    └── job_api.py         # Apify-powered LinkedIn & Naukri fetchers

---

🛠️ Tech Stack

Layer	Technology
UI	Streamlit
LLM	OpenAI GPT-4o
PDF parsing	PyMuPDF
Job scraping	Apify Client
Agent protocol	MCP / FastMCP
Config	python-dotenv
Package manager	uv

Apify actors used

Platform	Actor ID	Purpose
LinkedIn	hKByXkMQaC5Qt9UMN	Scrape LinkedIn job listings by title & location
Naukri	alpcnRV9YI9lYVPWk	Scrape Naukri.com jobs by keyword

---

⚙️ Configuration reference

Variable	Required	Description
OPENAI_API_KEY	✅	OpenAI API key for GPT-4o resume analysis
APIFY_API_KEY	✅	Apify token for LinkedIn & Naukri job actors

---

🧪 Development

# Install deps
uv sync

# Run Streamlit with auto-reload
uv run streamlit run app.py

# Run MCP server locally
uv run python mcp_server.py

---

📝 Notes

• Job scraping relies on Apify residential proxies for LinkedIn — usage is billed through your Apify account.
• Default job search location is india; pass a different location when calling the API or MCP tools.
• Resume uploads are processed in-memory; nothing is persisted to disk.
• The Streamlit app uses GPT-4o with temperature=0.5 for balanced, consistent outputs.

---

📄 License

This project is part of the MCP Bootcamp — Next-Gen AI Agents course. Use and modify freely for learning purposes.

---

Built with ❤️ for smarter job hunting

⭐ Star this repo if it helped you land your next role!