Name: Biomart MCP
Author: jzinno

LABSCO SUMMARY

Built with the context window in mind, which is why the answers stay usable.

Returning CSV instead of a formatted table is a deliberate choice by the author, because whitespace in a wide result eats most of the tokens. The same constraint sets the limit: asking for every gene on a chromosome will still be too large for the model to hold, so scope the filters before you run the query.

What it is

A Python server that sits on top of the pybiomart package and exposes Biomart as conversational tools. It is deliberately tools-only — no resources, no prompts — which the author chose for the widest client compatibility.

What you get

Mart and dataset discovery, so you can find the right dataset before querying it
Attribute and filter exploration for a dataset — the common ones or the full list
Data retrieval: query Biomart with the attributes and filters you picked
Identifier translation, for example gene symbols to Ensembl IDs
Results come back CSV-style rather than as a padded table, which keeps them far cheaper in context
Expensive lookups are cached in-process

Requirements

The Python package biomart-mcp, version 0.1.0, plus pybiomart. Install for Claude Desktop with uv run --with mcp[cli] mcp install --with pybiomart biomart-mcp.py, or add a uv command to .cursor/mcp.json. No credentials — Biomart is public.

Setup effort

Build from source — git clone https://github.com/jzinno/biomart-mcp.git

See installation options

USE CASES

01

Converting between identifier systems

Turn a list of gene symbols into Ensembl IDs mid-analysis instead of opening the Biomart web form.

02

Finding the right dataset first

List marts and datasets, then read that dataset's attributes and filters before composing a query.

03

Pulling annotation for a shortlist

Query with explicit filters so the result stays small enough to reason over.

BEFORE YOU INSTALL

What to know first

Requires

uv (the Claude Desktop and Cursor routes run it)
Python 3.10 or later

INSTALLATION

Connect your client

Server setup

TERMINAL

git clone https://github.com/jzinno/biomart-mcp.git
cd biomart-mcp

MCP Clients

Claude Desktop

CLAUDE DESKTOP · TERMINAL

uv run --with "mcp[cli]" mcp install --with pybiomart biomart-mcp.py

Run it inside the biomart-mcp folder you cloned; it registers biomart-mcp.py with Claude Desktop.

Cursor

CURSOR · JSON

{
  "mcpServers": {
    "Biomart": {
      "command": "uv",
      "args": [
        "run",
        "--with",
        "mcp[cli]",
        "--with",
        "pybiomart",
        "mcp",
        "run",
        "<YOUR_PATH_TO_BIOMART_MCP>"
      ]
    }
  }
}

<YOUR_PATH_TO_BIOMART_MCP> is the full path to biomart-mcp.py in the folder you cloned.

Biomart MCP