🚀 Resume Ranking MCP Server (FastMCP + Streamable HTTP)

A production-ready Model Context Protocol (MCP) server for AI-powered resume analysis and ranking. This server uses FastMCP and Streamable HTTP transport with Azure OpenAI models to provide scalable, modular, and intelligent resume evaluation APIs.

📦 Project Structure

mcp-http-server/
├── run_server.py
├── server_config.py
├── requirements.txt
├── .env (you create this)
├── src/
│   ├── mcp/
│   │   ├── http_server.py
│   │   ├── handlers.py
│   │   ├── tools.py
│   │   ├── error_handler.py
│   ├── core/
│   │   ├── analyzers.py
│   │   ├── parsers.py
│   │   ├── basic_info.py
│   │   ├── inflation.py
│   ├── utils/
│   │   └── config_manager.py
├── demo_data/
│   ├── jd/
│   ├── single_res/
│   ├── bulk_res/
├── demo_mcp/
│   ├── demo_script.py
│   ├── requirements.txt

✅ Prerequisites

• Python 3.10 to 3.13
• An Azure OpenAI resource with:
  • A deployed Chat/Completions model (e.g., GPT-4)
  • A deployed Embeddings model (e.g., text-embedding-3-small)
• Optional: Git, Docker, Node.js (for advanced integrations)

⚙️ Local Setup Instructions

1. Clone the Repository

git clone https://github.com/your-username/mcp-http-server.git
cd mcp-http-server

2. Create a Virtual Environment

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

3. Install Server Dependencies

pip install -r requirements.txt

4. Set Up Environment Variables

Create a .env file in the root folder with content like:

AZURE_OPENAI_API_KEY="your_api_key"
AZURE_OPENAI_ENDPOINT="https://your-resource.openai.azure.com/"
AZURE_OPENAI_MODEL="gpt-4"
AZURE_OPENAI_API_VERSION="2024-12-01-preview"
AZURE_EMBEDDING_MODEL="text-embedding-3-small"
MCP_SERVER_HOST=0.0.0.0
MCP_SERVER_PORT=8000
MAX_CONCURRENT_REQUESTS=10
ENABLE_PARALLEL_PROCESSING=true
MAX_WORKERS=4
SEMANTIC_WEIGHT=0.4
SKILL_WEIGHT=0.4
EXPERIENCE_WEIGHT=0.2
LOG_LEVEL=INFO

🚀 Running the Server

python run_server.py

• The MCP endpoint will be available at: http://localhost:8000/mcp

🧪 Run Demo Client

1. Setup Demo Environment

cd demo_mcp
python -m venv demo_env
source demo_env/bin/activate   # macOS/Linux
demo_env\Scripts\activate    # Windows
pip install -r requirements.txt

2. Run the Demo Script

python demo_script.py

• Tests health, connectivity, and performs sample analysis.
• Make sure the server is already running in another terminal.

🛠️ MCP Tools (APIs)

• health_check() – Server status & config check
• website_faq(question) – Returns company info/FAQ
• analyze_single_resume(jd_path, resume_path, skill_threshold)
• analyze_resumes_bulk(jd_path, resume_folder, skill_threshold)
• calculate_semantic_similarity_bulk(jd_path, resume_folder)

Testable via demo_script or any MCP-compatible client.

🧠 Core Modules

• parsers.py: Converts PDF/DOCX/TXT to clean text
• analyzers.py: Azure OpenAI powered skill extraction and scoring
• basic_info.py: Email, phone, LinkedIn extraction
• inflation.py: Adjusts composite scores
• config_manager.py: Loads .env and handles all configuration

🔐 Security Best Practices

• Do NOT commit .env to version control
• Use Key Vault or secret manager in production
• Clean up old resume files regularly
• Limit file size and validate extensions

📤 Deployment Recommendations

• Docker / Kubernetes / Azure App Service / Cloud Run are supported.
• Use API gateway for authentication and rate-limiting.
• Deploy MCP at /mcp endpoint.