I built a custom MCP (Model Context Protocol) Server using Node.js that connects multiple real-world data sources and APIs into a single, unified, AI-accessible system. The goal of this project was to provide structured and reliable context to AI assistants, enabling smarter automation and decision-making.

This MCP Server supports real-time weather data retrieval based on city names, delivering accurate temperature and weather conditions on demand. Alongside this, it integrates a database-driven HR module that manages job applications, tracks daily job-related activities, and retrieves up-to-date recruitment data.

The system also includes interview and schedule management, allowing recruiters and HR teams to access today’s interview schedules and job timelines from a centralized source. To ensure live and continuous updates, the platform uses Server-Sent Events (SSE) for real-time communication between services.

Designed with scalability in mind, the architecture follows a modular MCP server approach, where separate MCP services handle weather data, job applications, and scheduling independently. This makes it easy to extend the system with new services without impacting existing functionality.

Overall, this project demonstrates how MCP-based systems can power AI-ready platforms for recruitment, scheduling, and smart automation workflows by delivering clean, real-time, and well-structured contextual data.
I built a custom MCP (Model Context Protocol) Server using Node.js that connects multiple real-world data sources and APIs into a single, unified, AI-accessible system. The goal of this project was to provide structured and reliable context to AI assistants, enabling smarter automation and decision-making. This MCP Server supports real-time weather data retrieval based on city names, delivering accurate temperature and weather conditions on demand. Alongside this, it integrates a database-driven HR module that manages job applications, tracks daily job-related activities, and retrieves up-to-date recruitment data. The system also includes interview and schedule management, allowing recruiters and HR teams to access today’s interview schedules and job timelines from a centralized source. To ensure live and continuous updates, the platform uses Server-Sent Events (SSE) for real-time communication between services. Designed with scalability in mind, the architecture follows a modular MCP server approach, where separate MCP services handle weather data, job applications, and scheduling independently. This makes it easy to extend the system with new services without impacting existing functionality. Overall, this project demonstrates how MCP-based systems can power AI-ready platforms for recruitment, scheduling, and smart automation workflows by delivering clean, real-time, and well-structured contextual data.
Skills: Model Context Protocol (MCP) · Node.js · Server-Sent Events (SSE) · REST APIs · Database Design & Integration · AI Tooling & Context Engineering