mygene-mcp

nickzren/mygene-mcp

3.1

If you are the rightful owner of mygene-mcp and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

The MyGene MCP Server is a Model Context Protocol server that provides AI assistants with access to the MyGene.info API, offering a wide range of gene-related data and tools.

MyGene MCP Server

A Model Context Protocol (MCP) server that exposes the MyGene.info API as a set of tools for AI assistants.

Features

Core Capabilities

  • Gene Search: Query genes by symbol, name, Entrez ID, Ensembl ID, or other identifiers
  • Gene Annotations: Retrieve comprehensive gene information from multiple sources
  • Expression Queries: Search genes by tissue expression or retrieve expression profiles
  • Pathway Queries: Find genes in biological pathways or get pathway memberships
  • GO Annotations: Search by GO terms or retrieve GO annotations with evidence codes
  • Disease Associations: Find disease-associated genes or get gene-disease links
  • Drug/Chemical Interactions: Search genes by drug/chemical or get interaction data
  • Ortholog/Homology: Find orthologs across species or search homologous genes
  • Variant Information: Retrieve genetic variants and clinical significance
  • Batch Operations: Process up to 1000 genes in a single request
  • Genomic Interval Search: Find genes by chromosomal coordinates
  • Advanced Queries: Build complex queries with boolean logic and filters
  • Data Export: Export gene lists in TSV, CSV, JSON, or XML formats

Data Sources

  • NCBI: Entrez Gene, RefSeq, HomoloGene
  • Ensembl: Gene annotations, homology data
  • UniProt: Protein annotations, GO terms
  • Human Protein Atlas (HPA): Tissue expression, subcellular localization
  • GTEx: Gene expression in human tissues
  • BioGPS: Gene expression profiles
  • ExAC: Exome aggregation data
  • KEGG: Pathways and disease associations
  • Reactome: Biological pathways
  • WikiPathways: Community pathways
  • BioCarta: Pathway diagrams
  • NetPath: Signal transduction pathways
  • PID: Pathway Interaction Database
  • Gene Ontology: Functional annotations
  • DisGeNET: Disease-gene associations
  • ClinVar: Clinical variants
  • OMIM: Genetic disorders
  • PharmGKB: Pharmacogenomics
  • DrugBank: Drug targets
  • ChEMBL: Bioactive compounds
  • ChEBI: Chemical entities
  • InterPro: Protein families and domains
  • Pfam: Protein families
  • SMART: Protein domains
  • PANTHER: Gene function classification

Prerequisites

  • Python 3.12+ with pip

Quick Start

1. Install UV

UV is a fast Python package and project manager.

pip install uv

2. Install MCPM (MCP Manager)

MCPM is a package manager for MCP servers that simplifies installation and configuration.

pip install mcpm

3. Setup the MCP Server

cd mygene-mcp
uv sync

4. Add the Server to Claude Desktop

# Make sure you're in the project directory
cd mygene-mcp

# Set Claude as the target client
mcpm target set @claude-desktop

# Add the MyGene MCP server
mcpm import stdio mygene \
  --command "$(uv run which python)" \
  --args "-m mygene_mcp.server"

Then restart Claude Desktop.

Usage

Running the Server
uv run python -m mygene_mcp.server
Development
uv run pytest tests/ -v