TogoMCP: Natural Language Querying of Life-Science Knowledge Graphs via Schema-Guided LLMs and the Model Context Protocol (GitHub repo snapshot, v1.0.0)

Read full text
Authors: Yasunori Yamamoto, Akira R. Kinjo
Cited by: 0

Abstract

The source code of TogoMCP, a Model Context Protocol (MCP) server enabling natural-language queries to the RDF Portal, an integrated RDF database that aggregates roughly 60 life science data resources. This version is the one used in the Database paper. Changes since the last version: Now handles 28 life science databases (previously 23) Revised tool descriptions (docstrings) and LLM-friendly error messages. The new "find_databases" tool for more efficient database discovery. Reran the benchmark.

Fields of Study & Subjects

Semantic Web and Ontologies Biomedical Text Mining and Ontologies Natural Language Processing Techniques

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
8 March 2026
Language
EN