MCP Student Assistant

A beginner-friendly real-world mini project using Model Context Protocol (MCP) + Python + MySQL.

What it does

The MCP server exposes database operations as tools:

• get_student_marks

• get_attendance

• get_pending_assignments

• get_timetable

A client connects to the MCP server, discovers the tools, and calls them.

Related MCP server: College AI Assistant

Architecture

Student -> MCP Client -> MCP Server -> MySQL -> MCP Response

Tech Stack

• Python

• MCP Python SDK

• MySQL

• VS Code

• Git/GitHub

1. Create virtual environment

Windows PowerShell

python -m venv .venv
.venv\Scripts\Activate.ps1

macOS/Linux

python3 -m venv .venv
source .venv/bin/activate

2. Install packages

pip install -r requirements.txt

3. Configure MySQL

Create the database and sample data:

mysql -u root -p < database/student.sql

Or open database/student.sql in MySQL Workbench and run it.

Copy .env.example to .env and set your MySQL password.

4. Run the demo client

python client/ai_client.py

You should see the available MCP tools and a sample attendance result.

5. GitHub

git init
git add .
git commit -m "Initial MCP Student Assistant project"
git branch -M main
git remote add origin YOUR_GITHUB_REPOSITORY_URL
git push -u origin main

Important

Do not commit .env. It is already included in .gitignore.

Future upgrades

• Connect an LLM to the MCP client for natural-language questions.

• Add a web UI.

• Add authentication.

• Add teacher/admin tools.

• Add assignment reminders.