Inspiration
Preparing for placements can be confusing for students. Job descriptions list many skills, and it is not always easy to understand which skills we already have, what we are missing, and what to prepare first. I built Placement Readiness Copilot to make this process more organized and help students prepare based on the skills required for a role.
What it does
Placement Readiness Copilot is a placement preparation assistant built with Python, Streamlit, and the Model Context Protocol (MCP). It can:
- Analyze a job description and compare its required skills with a student's existing skills.
- Identify matching skills and missing skills.
- Generate a personalized, day-by-day preparation plan.
- Track preparation progress.
- Provide mock interview feedback based on keyword coverage.
- Connect the application to placement preparation tools through MCP.
How we built it
I built the application using Python and Streamlit for the user interface. I separated the placement preparation functions into reusable tools in tools.py. I created an MCP server in mcp_server.py to expose these functions as tools and an MCP client in mcp_client.py to call them from the Streamlit application. The main interface is in app_mcp.py.
The application uses rule-based logic for skill-gap analysis and preparation planning. The mock interview feedback uses keyword coverage rather than a full semantic evaluation model.
Challenges we faced
One of the main challenges was connecting the Streamlit application to the MCP server and making sure the tools returned results correctly. I also worked on organizing the code into separate modules, handling inputs, and testing the main features from the user interface.
What we learned
This project helped me understand how to structure a Python application, build an interactive interface, design reusable tools, and connect an application to an MCP server using Streamable HTTP. It also helped me understand how personalized preparation plans can turn a broad placement goal into manageable daily tasks.
What's next
Future improvements could include more detailed skill matching, adaptive preparation plans based on progress, and more advanced mock interview evaluation.
Built With
- fastmcp
- mcp
- python
- streamlit
