# Experiences with Model Context Protocol Servers for Science and High Performance Computing

arXiv: https://arxiv.org/abs/2508.18489 · HTML: https://mlsanity.com/paper/2508.18489/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Aug 2025.

## Built on by (most cited first, 6 of 6)

- [It's not the Language Model, it's the Tool: Deterministic Mediation for Scientific Workflows](https://mlsanity.com/paper/2605.13245/) (2026)
- [Toward Trustworthy Autonomous Science: A Two-Year Community Roadmap](https://mlsanity.com/paper/2607.12113/) (2026)
- [An Agentic Interface for End-to-End Probabilistic Seismic Hazard and Risk Analysis](https://mlsanity.com/paper/2607.16249/) (2026)
- [Schema-Bound LLM Control of Scientific Instrumentation through Model Context Protocol Skills](https://mlsanity.com/paper/2607.17012/) (2026)
- [Making Mathematical Knowledge Explainable, Accessible and Interoperable Through Large Language Model Integration](https://mlsanity.com/paper/2607.24512/) (2026)
- [Reputation as Community Memory for the Agentic Web](https://mlsanity.com/paper/2609.19502/) (2026)

## Abstract (arXiv)

Large language model (LLM)-powered agents are increasingly used to plan and execute scientific workflows, yet most research cyberinfrastructure (CI) exposes heterogeneous APIs and implements security models that present barriers for use by agents. We report on our experience using the Model Context Protocol (MCP) as a unifying interface that makes research capabilities discoverable, invokable, and composable. Our approach is pragmatic: we implement thin MCP servers over mature services, including Globus Transfer, Compute, and Search; status APIs exposed by computing facilities; Octopus event fabric; and domain-specific tools such as Garden and Galaxy. We use case studies in computational chemistry, bioinformatics, quantum chemistry, and filesystem monitoring to illustrate how this MCP-oriented architecture can be used in practice. We distill lessons learned and outline open challenges in evaluation and trust for agent-led science.