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

TL;DR

This paper introduces MCPmed, a standardized protocol to make bioinformatics web services more machine-readable, enabling better integration with large language models and automated research agents.

Contribution

It adapts the Model Context Protocol (MCP) for bioinformatics web servers, enhancing machine-readability, exploration, and interoperability for LLM-driven biomedical research.

Findings

Successful implementation across GEO, STRING, UCSC Cell Browser

Enhanced exploration capabilities with MCP-enabled LLMs

Structured transition improves automation and reproducibility

Abstract

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.