GWAS-MCP Server

Provides access to major biological databases via MCP for GWAS and bioinformatics research.
  • python

0

GitHub Stars

python

Language

4 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "zaeyasa-gwas-mcp": {
      "command": "python",
      "args": [
        "-m",
        "gwas_mcp.server"
      ]
    }
  }
}

You can leverage the GWAS-MCP server to access a wide range of bioinformatics databases through an MCP client. This server provides AI-assisted queries for gene and protein information, clinical variants, GWAS data, expression QTLs, interactions, structures, pathways, drug targets, and genetic disease associations, enabling streamlined research workflows within Claude Desktop or other MCP clients.

How to use

After you start the GWAS-MCP server, connect your MCP client and choose the gwas_mcp server as an available endpoint. You can issue natural language prompts to retrieve data from configured databases. For example, you can look up a gene or protein, check ClinVar interpretations for a specific variant, query the GWAS Catalog for associations, retrieve GTEx eQTL data, explore protein interactions, or examine AlphaFold structures and KEGG pathways. You can also combine queries to build multi-step analyses, such as identifying drug targets for a disease and then exploring related genetic variants.

How to install

Prerequisites: You need Python installed on your system. Optionally, you may use a Python virtual environment to isolate dependencies.

pip install gwas-mcp

Start the MCP server using Python. This runs the server module that powers the MCP endpoint.

python -m gwas_mcp.server

Configure Claude Desktop to load the MCP server by adding a new MCP entry. Provide the runtime command and arguments as shown.

{
  "mcpServers": {
    "gwas_bioinformatics": {
      "command": "python",
      "args": ["-m", "gwas_mcp.server"]
    }
  }
}

Place the configuration file in the appropriate location for your operating system and restart Claude Desktop to load the MCP server.

Configuration and usage notes

The server configuration shown enables you to run the MCP server locally and expose it to your MCP client without exposing a remote URL. No additional environment variables are required for the basic setup as described here.

Available tools and capabilities

The server exposes commands that cover protein and gene lookup, clinical variants, GWAS data, eQTL data, protein interactions, structural information, pathways, drug targets, and genetic diseases. For example: search_uniprot to locate proteins by name, get_protein_details for protein annotations, search_clinvar for clinical variant interpretations, get_eqtl_data for GTEx expression data, get_alphafold_structure for AI-predicted structures, and get_kegg_pathway to explore metabolic pathways.

Available tools

search_uniprot

Search UniProt by protein name, gene, or ID to retrieve protein information.

get_protein_details

Obtain detailed protein information including functions, domains, and GO terms.

search_ncbi_gene

Query the NCBI Gene database for gene information.

search_ensembl_gene

Fetch gene location and details from the Ensembl database.

get_variant_info

Retrieve SNP/variant information by rsID.

get_interpro_domains

Get protein domain information from InterPro.

search_clinvar

Search ClinVar for clinical variant interpretations.

get_clinvar_variant

Get clinical interpretation for a specific variant.

annotate_snps

Annotate SNPs with functional consequences.

query_gwas_catalog

Query the GWAS Catalog for genome-wide association study associations.

get_eqtl_data

Fetch GTEx expression quantitative trait loci data.

get_protein_interactions

Find protein-protein interactions from STRING.

get_interaction_network

Retrieve interaction networks among multiple proteins.

get_functional_enrichment

Perform pathway and GO enrichment analyses.

get_alphafold_structure

Obtain AI-predicted protein structures from AlphaFold.

search_alphafold

Search the AlphaFold database for protein structures.

search_pdb_structures

Search the Protein Data Bank for 3D structures.

get_pdb_structure

Retrieve details of a PDB structure.

search_kegg_pathway

Search KEGG pathways and related information.

get_kegg_pathway

Get pathway genes and detailed pathway information.

get_gene_pathways

Find pathways associated with a gene.

get_drug_targets

Identify drugs targeting a gene using Open Targets.

get_disease_associations

Retrieve disease associations with scores for genes.

search_open_targets

Search genes, diseases, or drugs in Open Targets.

search_pharmgkb

Query PharmGKB for pharmacogenomics data.

get_drug_gene_interactions

Fetch drug-gene interactions.

search_omim

Search OMIM for genetic diseases.

get_gene_diseases

List diseases associated with a gene.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational