Labsco
MCP SERVER

DROMA MCP Server

by mugpeng ↗

Load cancer drug-response and omics datasets into memory and ask about them in plain language, with the DROMA R packages doing the analysis underneath.

Biomedical: Genomics & Clinical Data
Summary
Pharmacogenomics datasets you can ask about rather than script against.

It carries the loading, normalisation and caching that usually take a page of R at the top of every analysis, so a question about a drug-omics association starts at the question.

What it is

An MCP server for DROMA, the Drug Response Omics association MAp. It sits in front of the DROMA.R and DROMA.Set R packages over rpy2, loading pharmacogenomics datasets such as CCLE and gCSI into memory and answering questions against them.

What you get
  • A DROMA dataset loaded from the SQLite database and held in memory
  • Several projects loaded at once and worked with together
  • Molecular profiles loaded with z-score normalisation applied
  • Treatment response data loaded with the same normalisation
  • The active dataset switched, the loaded ones listed, and any of them unloaded to free memory
  • Results exported to CSV, Excel or JSON
  • Transport over STDIO, HTTP or SSE
Requirements

Python 3.10 or newer, a recent R with the DROMA.Set and DROMA.R packages installed, and a DROMA SQLite database. Without the R side in place the server has nothing to call.