{"ID":2878754,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.18489","arxiv_id":"2508.18489","title":"Experiences with Model Context Protocol Servers for Science and High Performance Computing","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2508.18489","url_pdf":"https://arxiv.org/pdf/2508.18489v1","authors":"[\"Haochen Pan\",\"Ryan Chard\",\"Reid Mello\",\"Christopher Grams\",\"Tanjin He\",\"Alexander Brace\",\"Owen Price Skelly\",\"Will Engler\",\"Hayden Holbrook\",\"Song Young Oh\",\"Maxime Gonthier\",\"Michael Papka\",\"Ben Blaiszik\",\"Kyle Chard\",\"Ian Foster\"]","published":"2025-08-25T21:02:33Z","proceeding":"cs.DC","tasks":"[\"cs.DC\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}