{
  "abstract": "Recent improvements in large language models (LLMs) have had a dramatic effect on capabilities and productivity across many disciplines involving critical thinking and writing. The development of the model context protocol (MCP) provides a way to extend the power of LLMs to a specific set of tasks or scientific equipment with help from curated tools and resources. Here, we describe a framework called TEM Agent designed for transmission electron microscopy (TEM) that leverages the benefits of LLMs through a MCP approach. We simultaneously access and control several subsystems of the TEM, a data management platform, and high performance computing resources through text-based instructions. We demonstrate the abilities of the TEM Agent to set up and complete intricate workflows using a simplified set of MCP tools and resources accompanying a commercial LLM without any additional training. The use of a framework such as the TEM Agent simplifies access to complex microscope ecosystems comprised of several vendor and custom systems enhancing the ability of users to accomplish microscopy experiments across a range of difficulty levels.",
  "abstract_shown": true,
  "affiliations": [
    "The Molecular Foundry, Lawrence Berkeley National Laboratory, Berkeley, CA, USA"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 5,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Morgan K. Wall"
    },
    {
      "affs": [
        0
      ],
      "name": "Alexander J. Pattison",
      "orcid": "0000-0001-7869-8910"
    },
    {
      "affs": [
        0
      ],
      "name": "Edward S. Barnard",
      "orcid": "0000-0003-4736-0743"
    },
    {
      "affs": [
        0
      ],
      "name": "Stephanie M. Ribet",
      "orcid": "0000-0002-7117-066X"
    },
    {
      "affs": [
        0
      ],
      "name": "Peter Ercius",
      "orcid": "0000-0002-6762-9976"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/9r9xnfp3f4wtm.bib",
  "cited_by": 14,
  "doi": "10.1038/s41524-026-02103-z",
  "fulltext_url": null,
  "id": "9r9xnfp3f4wtm",
  "issns": [
    "2057-3960"
  ],
  "landing_url": "https://doi.org/10.1038/s41524-026-02103-z",
  "language": "en",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "1315|Advanced Electron Microscopy Techniques and Applications"
    ]
  ],
  "openalex": "W4416235084",
  "pdf_url": "https://www.nature.com/articles/s41524-026-02103-z_reference.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-06-10",
  "publisher": "Nature Portfolio",
  "ris": "https://research.draconitic.com/paper/9r9xnfp3f4wtm.ris",
  "sources": [
    {
      "first_seen": "2026-11-07T13:20:47Z",
      "native_id": "W4416235084",
      "source": "openalex",
      "url": "https://doi.org/10.1038/s41524-026-02103-z"
    }
  ],
  "subjects": [
    {
      "field": "biochemistry",
      "origin": "openalex:1315|Advanced Electron Microscopy Techniques and Applications",
      "subfield": "structural-biology"
    }
  ],
  "title": "TEM Agent: enhancing transmission electron microscopy with modern AI tools",
  "title_text": "TEM Agent: enhancing transmission electron microscopy with modern AI tools",
  "type": "peer-reviewed",
  "updated_at": "2026-11-09T13:21:05Z",
  "url": "https://research.draconitic.com/paper/9r9xnfp3f4wtm",
  "venue": "npj Computational Materials",
  "versions": []
}