Command Palette

Search for a command to run...

UnylyUnyly
Browse all

Pgx

FreeNot checked

Enables real-time pharmacogenomics analysis, including variant clinical significance, drug-gene interactions, and dosing guidelines, by connecting to ClinVar, P

GitHubEmbed

About

Enables real-time pharmacogenomics analysis, including variant clinical significance, drug-gene interactions, and dosing guidelines, by connecting to ClinVar, PharmGKB, gnomAD, and other databases.

README

CI PyPI Python License: MIT

An open-source MCP server that gives Claude real-time access to pharmacogenomics databases — turning genetic variant lookups and drug interaction checks from a 45-minute manual workflow into a single conversation.

Features

  • ClinVar: Variant clinical significance and pathogenicity
  • PharmGKB: Drug-gene interactions, clinical annotations, CPIC/DPWG dosing guidelines
  • gnomAD: Population allele frequencies across ancestries
  • Open Targets: Drug-target-disease associations, pharmacogenomics evidence
  • ClinicalTrials.gov: Clinical trial search (US and international)

Installation

pip install pgx-mcp

Or with uvx:

uvx pgx-mcp

Claude Desktop Configuration

Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "pgx-mcp": {
      "command": "uvx",
      "args": ["pgx-mcp"]
    }
  }
}

For local development:

{
  "mcpServers": {
    "pgx-mcp": {
      "command": "uv",
      "args": ["--directory", "/path/to/mcp-pharmacogenomics", "run", "pgx-mcp"]
    }
  }
}

Available Tools

Tool Source Description
lookup_variant_clinvar ClinVar Variant clinical significance
search_gene_variants_clinvar ClinVar List variants in a gene
get_drug_gene_interactions PharmGKB Clinical annotations for drug-gene pairs
get_drug_info PharmGKB Drug details and cross-references
get_dosing_guideline PharmGKB CPIC/DPWG dosing recommendations
search_drug_targets Open Targets Drug mechanisms, indications, PGx evidence
get_variant_frequency gnomAD Population allele frequencies
search_clinical_trials ClinicalTrials.gov Trial search with filters
get_trial_details ClinicalTrials.gov Full trial details
pgx_consultation All Comprehensive PGx consultation report

Example Usage

Ask Claude:

"My patient is a CYP2D6 poor metabolizer (*4/*4) and needs pain management. What should I prescribe?"

"What are the CPIC guidelines for clopidogrel and CYP2C19?"

"Are there any recruiting pharmacogenomics clinical trials in Germany?"

Configuration

All settings are optional and configured via environment variables (or a .env file):

Variable Default Description
PGX_MCP_NCBI_API_KEY None NCBI API key for higher ClinVar rate limits (3/s → 9/s)
PGX_MCP_CACHE_TTL_SECONDS 3600 Cache duration in seconds

Development

git clone https://github.com/Julius-Schmidt/mcp-pharmacogenomics.git
cd mcp-pharmacogenomics
pip install -e ".[dev]"
pytest

Roadmap

  • Demo video/GIF in README
  • EU Clinical Trials Register integration (currently no public API — European trials are covered through ClinicalTrials.gov registrations)
  • PharmVar star-allele nomenclature lookups
  • FDA Pharmacogenomic Biomarkers table integration

License

MIT

from github.com/Julius-Schmidt/mcp-pharmacogenomics

Install Pgx in Claude Desktop, Claude Code & Cursor

Recommended · one command, every IDE
unyly install pgx-mcp

Installs into Claude Desktop, Claude Code, Cursor & VS Code — handles npx, uvx and build-from-source repos for you.

First time? Get the CLI: curl -fsSL https://unyly.org/install | sh

Or configure manually

Run in your terminal:

claude mcp add pgx-mcp -- uvx pgx-mcp

FAQ

Is Pgx MCP free?

Yes, Pgx MCP is free — one-click install via Unyly at no cost.

Does Pgx need an API key?

No, Pgx runs without API keys or environment variables.

Is Pgx hosted or self-hosted?

A hosted option is available: Unyly runs the server in the cloud, no local setup required.

How do I install Pgx in Claude Desktop, Claude Code or Cursor?

Open Pgx on unyly.org, pick your client tab (Claude Desktop, Claude Code, Cursor) and press Install — the config is generated automatically, no JSON editing.

Related MCPs

Compare Pgx with

Not sure what to pick?

Find your stack in 60 seconds

Author?

Embed badge for your README

Browse similar

All development MCPs