AI-Powered Library Management System Using Model Context Protocol and Large LanguageModels

Abstract

This work presents the design and implementation of an AI-powered Library Management System (LMS) that combines the Model Context Protocol (MCP) with a cloud-based large language model to interact via a smart library assistant called LibraBot. Instead of rigid keyword-based search, the system offers a natural-language chat interface built on the Ollama Cloud LLM and the SmolAgents framework. Nine dedicated MCP tools cover core library workflows, including checking item availability, locating items, managing reservations, and recommending books based on content, all integrated with a catalog of over one hundred B.Tech engineering titles stored in SQLite and Excel and exposed through a multi-page Flask web interface. Personalized recommendations rely on a TF–IDF cosine-similarity model that operates purely on content features and does not require historical user interaction data. In 70 test scenarios, the system achieved a 100% success rate, with an average response time of 1.2 seconds and uptime reaching 99.5% under concurrent loads of up to 150 users, demonstrating that MCP-based tool integration with LLM reasoning can deliver a scalable, always-available alternative to traditional library management approaches.