EUVIMEDEUVIMED entdecken
StudienprotokollOpen Access · CC BY 4.0

MCPmed: a call for Model Context Protocol-enabled bioinformatics web services for LLM-driven discovery

Matthias Flotho iD, Ian Ferenc Diks, Philipp Flotho, Leidy-Alejandra G Molano, Pascal Hirsch, Andreas Keller iD

Briefings in Bioinformatics · 2026

DOI: 10.1093/bib/bbag076 ↗

Kurz gefasst

Studienprotokoll in der Zeitschrift Briefings in Bioinformatics, 2026. Verfasst von Matthias Flotho und 5 weiteren Autor:innen. Beteiligte Einrichtung: Chair for Clinical Bioinformatics, Center for Bioinformatics, Saarland University, Saarland University Campus, 66123 Saarland, Germany. Hauptthemen laut MEDLINE: Computational Biology, Internet, Software. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: DFG, M.J. Fox Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Bioinformatics web servers are critical resources in modern biomedical research, facilitating interactive exploration of datasets through custom-built interfaces with rich visualization capabilities. However, this mostly human-centric design limits machine readability for large language models (LLMs) and deep research agents. We address this gap by adapting model context protocol (MCP) to bioinformatics web server backends, a standardized, machine-actionable layer that explicitly associates web service endpoints with scientific concepts and detailed metadata. Our implementations across widely used databases (GEO, STRING, and UCSC Cell Browser) demonstrate enhanced exploration capabilities through MCP-enabled LLMs. To accelerate adoption, we propose MCPmed, a community effort supplemented by lightweight breadcrumbs for services not yet fully MCP-enabled and templates for setting up new servers. This structured transition aims to significantly enhance automation, reproducibility, and interoperability, preparing bioinformatics web services for next-generation research agents.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Computational BiologyInternetSoftwareLarge Language ModelsHumansDatabases, FactualUser-Computer Interface

Stichwörter der Autor:innen

APIGEOLLMMCPdatabaseweb server

Autor:innen und Institutionen

  • Chair for Clinical Bioinformatics, Center for Bioinformatics, Saarland University, Saarland University Campus, 66123 Saarland, Germany.
  • Helmholtz Institute for Pharmaceutical Research Saarland (HIPS), Saarland University, Saarland University Campus, 66123 Saarland, Germany.
  • Pharma Science Hub (PSH), Saarland University Campus, Saarland University Campus, 66123 Saarland, Germany.

ORCID-Profile: Matthias Flotho, Andreas Keller

Förderung

  • DFG
  • M.J. Fox Foundation

Zitieren

APA

Flotho, M., Diks, I. F., Flotho, P., Molano, L. G., Hirsch, P., & Keller, A. (2026). MCPmed: a call for Model Context Protocol-enabled bioinformatics web services for LLM-driven discovery. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbag076

Vancouver

Flotho M, Diks IF, Flotho P, Molano LG, Hirsch P, Keller A. MCPmed: a call for Model Context Protocol-enabled bioinformatics web services for LLM-driven discovery. Briefings in Bioinformatics. 2026. doi:10.1093/bib/bbag076

BibTeX
@article{Flotho2026,
  author = {Flotho, Matthias and Diks, Ian Ferenc and Flotho, Philipp and Molano, Leidy-Alejandra G and Hirsch, Pascal and Keller, Andreas},
  title = {MCPmed: a call for Model Context Protocol-enabled bioinformatics web services for LLM-driven discovery},
  journal = {Briefings in Bioinformatics},
  year = {2026},
  doi = {10.1093/bib/bbag076}
}
Kostenlos starten →