MCPmed: A Call for MCP-Enabled Bioinformatics Web Services for LLM-Driven Discovery

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Flotho, Matthias, Diks, Ian Ferenc, Flotho, Philipp, Molano, Leidy-Alejandra G., Hirsch, Pascal, Keller, Andreas
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912921966084096
author Flotho, Matthias
Diks, Ian Ferenc
Flotho, Philipp
Molano, Leidy-Alejandra G.
Hirsch, Pascal
Keller, Andreas
author_facet Flotho, Matthias
Diks, Ian Ferenc
Flotho, Philipp
Molano, Leidy-Alejandra G.
Hirsch, Pascal
Keller, Andreas
contents 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 human-centric design limits machine readability for large language models (LLMs) and deep research agents. We address this gap by adapting the Model Context Protocol (MCP) to bioinformatics web server backends - a standardized, machine-actionable layer that explicitly associates webservice endpoints with scientific concepts and detailed metadata. Our implementations across widely-used databases (GEO, STRING, 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 significantly enhances automation, reproducibility, and interoperability, preparing bioinformatics web services for next-generation research agents.
format Preprint
id arxiv_https___arxiv_org_abs_2507_08055
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MCPmed: A Call for MCP-Enabled Bioinformatics Web Services for LLM-Driven Discovery
Flotho, Matthias
Diks, Ian Ferenc
Flotho, Philipp
Molano, Leidy-Alejandra G.
Hirsch, Pascal
Keller, Andreas
Other Quantitative Biology
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 human-centric design limits machine readability for large language models (LLMs) and deep research agents. We address this gap by adapting the Model Context Protocol (MCP) to bioinformatics web server backends - a standardized, machine-actionable layer that explicitly associates webservice endpoints with scientific concepts and detailed metadata. Our implementations across widely-used databases (GEO, STRING, 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 significantly enhances automation, reproducibility, and interoperability, preparing bioinformatics web services for next-generation research agents.
title MCPmed: A Call for MCP-Enabled Bioinformatics Web Services for LLM-Driven Discovery
topic Other Quantitative Biology
url https://arxiv.org/abs/2507.08055