A lightweight AI Study Assistant MCP server built with FastMCP, SQLite, and Google Gemini.
View on GitHub ↗A lightweight AI Study Assistant MCP Server built with Python, FastMCP, SQLite, and Google Gemini.
The project demonstrates how the Model Context Protocol (MCP) can connect an AI client with custom tools for managing study notes and accessing an AI study assistant.
- Add study notes - View saved notes - Search notes by subject, title, or content - Delete notes - Persistent storage using SQLite
- Ask study-related questions - Explain difficult concepts - Summarize topics - Generate simple explanations for revision - Powered by Google Gemini
- Python - FastMCP - Model Context Protocol (MCP) - SQLite - Google Gemini API - python-dotenv
The server currently exposes the following tools:
Tool Description ------------- -------------------------------- hello Tests the MCP server connection addnote Saves a new study note getnotes Retrieves all saved notes findnotes Searches saved notes removenote Deletes a note by title askai Sends a study question to Gemini
.env and the local SQLite database should not be committed to GitHub.
Never commit your actual API key to GitHub.
The server runs using the STDIO transport and waits for an MCP client connection.
The Inspector allows you to discover and call all tools exposed by the MCP server.
Sensitive values are stored using environment variables.
The following files should not be committed:
- PDF-based question answering - Retrieval-Augmented Generation (RAG) - Flashcard generation - Quiz generation - Study planning - Vector database integration - Remote MCP transport - Web interface
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/TapanSreesailam--AI-Study-Assistant-MCP.html)
Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is
zhuyansen/new-term-radarDaily radar for new AI terms: names of new models, products and repos, caught on X, Hugging Face, GitHub and sitemaps before keyword tools list them.
yzg1226/mcd-party-officer🍟 麦当劳门店派对成团调度 Skill — 把派对从「策划」推进到「办得成」：成团概率雷达 / 包场vs拼团 / 择日黄历 / 儿童营养指数 / 招募卡与邀请函
fellowgeek/mcp-memoryAn OKF-backed Model Context Protocol (MCP) server delivering persistent long-term memory and SQLite FTS5 search for AI agents.
hirotomasato/yowesGenerate realistic teacher documents (ID cards, licenses, letters) for 13 countries via MCP.
hujjun/mcd-saver-strategist麦当劳省钱点餐助手（麦门精算师）｜麦当劳优惠券组合优化 Skill：拉取麦当劳菜单与全部可用优惠券，算出最省的点餐组合，巨无霸套餐 ¥47 → ¥21.9（省 53%）。McDonalds MCP（麦当劳 MCP）coupon optimizer · McDonalds China MCP Server · Agent Skill for WorkBuddy · 麦当劳程序员创意开发大赛参赛作品
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.