MCP-Server
Enables querying a structured CV and sending test emails via Ethereal through a backend API.
README
MCP Server & Frontend โ Coding Challenge
This project was built as part of a coding challenge to demonstrate API design, integration skills, and a simple frontend playground. It includes both a backend MCP server and a Next.js frontend.
๐น Features
Backend (MCP Server)
-
Chat about CV โ Answers questions about my resume from a structured JSON file (
cv.json).-
Example questions:
- "What role did I have at my last position?"
- "What projects have you built?"
- "What skills do you know?"
- "Whatโs your education?"
-
-
Send Email Notifications โ Provides an endpoint to send emails (recipient, subject, body) using Nodemailer with Ethereal (test inbox).
Frontend (Next.js Playground)
-
A minimal UI with two sections:
- CV Query Box โ Enter a question and see the serverโs response.
- Email Form โ Fill in recipient, subject, and body, then send an email through the backend.
๐น Tech Stack
- Backend: Node.js, Express
- Email: Nodemailer (Ethereal for testing)
- Frontend: Next.js (React)
- Deployment: Render (backend) + Vercel (frontend)
๐น Live Links
- Backend Repo: MCP-Server
- Backend Live: https://mcp-server-nze2.onrender.com
- Frontend Repo: MCP-Frontend
- Frontend Live: https://mcp-frontend-two.vercel.app/
๐น Local Setup
1. Clone repos
# Backend
git clone https://github.com/dilshankavishka/MCP-Server.git
cd MCP-Server
# Frontend
git clone https://github.com/dilshankavishka/MCP-Frontend.git
cd MCP-Frontend
2. Install dependencies
npm install
3. Run backend
cd MCP-Server
node server.js
Server should start on http://localhost:5000
4. Run frontend
cd MCP-Frontend
npm run dev
Frontend should start on http://localhost:3000
๐น Example Usage
CV Query
POST http://localhost:5000/cv-query
{
"question": "What role did I have at my last position?"
}
Response:
{
"answer": "Your last role was Software Engineer Intern at SimpliFy Labs (LK) (Feb 2025 - Jul 2025)."
}
Send Email
POST http://localhost:5000/send-email
{
"recipient": "test@example.com",
"subject": "Hello from MCP",
"body": "This is a test email via Ethereal ๐"
}
Response:
{
"status": "success",
"message": "Email sent (preview URL below)",
"preview": "https://ethereal.email/message/YOUR-PREVIEW-LINK"
}
๐ Open the preview link to view the test email.
๐น Notes on Approach
- The CV is stored in JSON for structured querying (instead of live parsing).
- A simple keyword-based matcher powers the
/cv-queryendpoint. - Emails use Ethereal for testing (no real delivery, but full previews).
- Deployment handled via Render (API) and Vercel (frontend UI).
โ With this setup, you can query my CV, send test emails, and interact with everything through a live frontend demo.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.