CropOntologyMCP: Restricted FastMCP Server and Ingestion Pipeline for Multi-Crop Trait Ontologies (SQLite)

This dataset contains restricted research software implementing CropOntologyMCP, a FastMCP server that provides structured tools to search and retrieve crop ontology trait and variable metadata across multiple crops from a local SQLite database. The package includes (1) an ingestion script that downloads Crop Ontology Excel reports from cropontology.org for a curated list of crops, normalizes and consolidates the tables, and builds an SQLite database table (ontology); and (2) an MCP server that connects to the SQLite database on startup and exposes tools such as search_traits, get_scale_and_synonyms, and get_variable_info to query traits, variables, scales, categories, and synonyms by crop. Source data are obtained from Crop Ontology reports (https://cropontology.org/). The deposited files are restricted because they currently contain non-public software. Terms of use: These data and documents are licensed under a Creative Commons Attribution 4.0 International license. You may copy, distribute and transmit the data as long as you acknowledge the source through proper data citation. Disclaimer: Whilst utmost care has been taken by CIP and data authors while collecting and compiling the data, the data is however offered "as is" with no express or implied warranty. In no event shall the data authors, CIP, or relevant funding agencies be liable for any actual, incidental or consequential damages arising from use of the data. By using the CIP Dataverse, the user expressly acknowledges that the Data may contain some nonconformities, defects, or errors. No warranty is given that the data will meet the user's needs or expectations or that all nonconformities, defects, or errors can or will be corrected. The user should always verify actual data; therefore the user bears all responsibility in determining whether the data is fit for the user’s intended use. The user of the data should use the related publications as a baseline for their analysis whenever possible. Related publications are listed in the metadata section of the Dataverse study.