MCP Resume & Email Assistant

This is a Model Context Protocol (MCP) server that provides the following features:

1. Resume Parsing: Parse and extract information from your resume to answer questions about your professional experience.
2. Email Notifications: Send email notifications with customizable recipient, subject, and body.
3. Next.js Frontend: A beautiful, responsive UI for interacting with the MCP server.
4. GitHub Pages Deployment: The frontend is configured for easy deployment to GitHub Pages.

Live Demo

Check out the live demo at: https://ThambimuthuAnush24.github.io/mcp-server

Project Structure

mcp-server/
├── src/
│   ├── index.ts           # Main MCP server implementation
│   ├── localClient.ts     # Test client for local development
│   ├── services/
│   │   ├── emailService.ts # Email service implementation
│   │   └── resumeService.ts # Resume parsing service
├── frontend/              # Next.js frontend application
│   ├── src/
│   │   ├── app/           # Next.js app directory
│   │   │   ├── api/       # API routes
│   │   │   ├── layout.tsx # Main layout
│   │   │   └── page.tsx   # Main page
│   │   ├── components/    # React components
│   │   └── utils/         # Utility functions
├── .vscode/
│   └── mcp.json           # VS Code MCP integration
├── .env                   # Environment variables (not committed)
├── package.json           # Project dependencies
└── tsconfig.json          # TypeScript configuration

Features

• 📄 Resume Parser: Upload and analyze resumes with intelligent extraction
• 📧 Email Sender: Create and send professional emails with ease
• 💬 AI Assistant: Get intelligent answers to questions about your resume and career
• 🎨 Beautiful UI: Modern glass-morphism design with animations and responsive layout
• 🚀 GitHub Pages Deployment: Easy deployment to GitHub Pages

Technologies Used

• Next.js 14: For the frontend with static export support
• TypeScript: For type-safe code
• Tailwind CSS: For beautiful, responsive styling
• Model Context Protocol (MCP): For AI-powered features
• GitHub Pages: For deployment

Prerequisites

• Node.js v18 or higher
• npm or yarn
• Git

Setup Instructions

For Backend Development

1. Clone this repository
2. Install dependencies:

   npm install
   

3. Create a .env file in the root directory with your email configuration
4. Build the project:

   npm run build
   

5. Start the server:

   npm start
   

For Frontend Development

1. Navigate to the frontend directory:

   cd frontend
   

2. Install dependencies:

   npm install
   

3. Start the development server:

   npm run dev
   

4. Open http://localhost:3000 in your browser

GitHub Pages Deployment

This project is configured for deployment on GitHub Pages. Follow these steps to deploy:

1. Make sure you've pushed your code to GitHub:

   git add .
   git commit -m "Ready for GitHub Pages deployment"
   git push origin main
   

2. Run the deployment script:

   cd frontend
   npm run deploy
   

This will:

• Build the Next.js application
• Create the necessary .nojekyll file
• Deploy to the gh-pages branch
• Make your site available at https://yourusername.github.io/mcp-server

GitHub Pages Mode

When running on GitHub Pages, the application automatically detects the environment and uses mock data instead of trying to call backend APIs that wouldn't be available in a static deployment.

MCP Tools Provided

1. parseResume

   • Parses a resume from text or PDF
   • Parameters:
     • text (optional): Plain text resume content
     • fileContent (optional): Base64-encoded PDF content
     • fileName (optional): Name of the PDF file

2. queryResume

   • Queries parsed resume data
   • Parameters:
     • query: The question to ask about the resume
     • context (optional): Previous conversation history

3. sendEmail

   • Sends an email
   • Parameters:
     • to: Recipient email address
     • subject: Email subject
     • body: Email content

Local Development

Local Testing

The backend includes a local client for testing MCP tools:

npm run test:local

Debugging

For debugging the MCP server:

1. Run in development mode:

   npm run dev
   

2. Check the console logs for any errors.

3. For frontend debugging, use the browser's developer tools.

License

MIT