A research article by Dr. Yasunori Yamamoto of DBCLS and his co-authors titled “TogoMCP: natural language querying of life-science knowledge graphs via schema-guided LLMs and the Model Context Protocol” has been published.
The article is open access and is available via the DOI link below.

Kinjo, A. R., Yamamoto, Y., Bustamante-Larriet, S., Labra-Gayo, J.-E., & Fujisawa, T. (2026). TogoMCP: Natural Language Querying of Life-Science Knowledge Graphs via Schema-Guided LLMs and the Model Context Protocol. Database 2026:baag042. https://doi.org/10.1093/database/baag042

TogoMCP uses the Model Context Protocol (MCP) to connect external large language models with knowledge bases, including the RDF portal, and facilitates effective knowledge acquisition.
In an evaluation covering 23 knowledge bases, TogoMCP showed a significant improvement in question-answering performance.
This achievement is expected to serve as a foundation for the efficient utilisation of life science data without requiring expertise in specialized query languages.