G.Rama Devi , N. Amrutha,1P. Sirisha ,1S. Madhu ,1S. Mahesh 03 3(1) Museums are living archives of human civilisation that face a growing challenge delivering personalised contextually rich visitor guidance at scale without proportionally expanding human staffing Existing chatbot solutions built on patternmatching intent classification or knowledge graph paradigms fall short when visitors ask emotional openended or crossexhibit questions and they demand constant manual updates whenever collection content changes This paper presents a museum chatbot architecture that pairs the generative strength of Large Language Models with the structured permissionenforced data access of Model Context Protocol servers The LLM manages natural multiturn conversation contextual memory dynamic tone adaptation and multilingual generation while the MCP layer acts as a secure gateway that retrieves verified realtime exhibit information from the museum database without model retraining or script edits A fourtier designvisitor interface LLM processing MCP communication and museum databasesupports instant content propagation Evaluation through seven functional test cases confirms stable conversation continuity reliable multilingual switching effective restricteddata filtering and graceful handling of ambiguous queries The system improves visitor engagement reduces staff maintenance overhead and establishes a scalable privacyconscious template for AIpowered digital guides across art galleries cultural centres and heritage institutions Copyright (c) Journal of Science Engineering Technology and Management Science. All rights reserved 2026