Sambalpuri Sarees in the Digital Loom: Metadata Schema and Natural Language Query Interface Design

Sambalpuri sarees, traditional handloom textiles from Odisha, India, embody rich cultural heritage through their unique bandha (ikat) weaving techniques and symbolic motifs. Despite their historical and artistic value, digital documentation of these sarees remains inadequate due to the lack of structured, domain-specific metadata and user-friendly retrieval systems. This study addresses these gaps by developing a customized metadata schema that extends the Dublin Core standard with textile-specific elements tailored to Sambalpuri sarees. The schema is implemented within the open-source DSpace repository platform, and enhanced with a natural language query interface powered by a Claude AI-based Model Context Protocol (MCP) server. The system enables intuitive, multilingual access to digital saree records, improving both discoverability and user experience. Evaluation confirms effective metadata ingestion, accurate semantic retrieval, and broad accessibility. This approach offers a scalable solution for preserving and promoting intangible cultural heritage in the digital age.