CIViC MCP: Integrating Large Language Models with the Clinical Interpretations of Variants in Cancer

  1. Lars Schimmelpfennig
  2. Quentin Cody
  3. Joshua McMichael
  4. Adam C. Coffman
  5. Jason Saliba
  6. Arpad Danos
  7. Susanna Kiwala
  8. Alex Wagner
  9. Javier Sanz-Cruzado
  10. Jake Lever
  11. Malachi Griffith
  12. Obi L. Griffith
0 evaluations Published on
Read the full article Related papers
This article on Sciety

Abstract

Summary

The Clinical Interpretation of Variants in Cancer (CIViC) knowledgebase provides a community-driven, open-source platform for discussing the biological and Clinical Significance of molecular variants in cancer. To enable users to make complex connections between CIViC information, we developed the CIViC Model Context Protocol (MCP) server, which allows large language models (LLMs) to directly interface with the CIViC API through natural language, facilitating the rapid summarization of expertly curated cancer variant interpretations.

Availability and implementation

The CIViC MCP server is detailed at <ext-link xmlns:xlink="http://www.w3.org/1999/xlink" ext-link-type="uri" xlink:href="https://github.com/griffithlab/civic-mcp-server">https://github.com/griffithlab/civic-mcp-server</ext-link> with archived code and evaluation data deposited in Zenodo (DOI: 10.5281/zenodo.17344050). The repository is a fork of <ext-link xmlns:xlink="http://www.w3.org/1999/xlink" ext-link-type="uri" xlink:href="https://github.com/QuentinCody/civic-mcp-server">https://github.com/QuentinCody/civic-mcp-server</ext-link> (QuentinCody 2025) and includes instructions for accessing the server through the Claude desktop app and hosting it locally with GPT-5. We also provide a Python script for directly querying the MCP server.

Supplemental information

Supplementary data are available at Bioinformatics online.

Related articles

Related articles are currently not available for this article.