1000 Genomes Project dataset MCP Server

Natural language access to 1000 Genomes Project dataset, hosted online in Dnaerys variant store

Dataset is sequenced & aligned to GRCh38 by New York Genome Center

• 2504 unrelated samples from the phase three panel
• additional 698 samples, related to samples in the 2504 panel
  • 3202 samples total (1598 males, 1604 females)
• dataset details

Key Features

• real-time access to 138 044 724 unique variants and about 442 billion individual genotypes in 3202 samples

• variant, sample, and genotype selection based on coordinates, annotations, zygosity

• filtering by VEP, ClinVar, gnomAD AF and AlphaMissense annotations

• filtering by inheritance model (de novo, heterozygous dominant, homozygous recessive)

Deployments

Remote MCP service is available online via Streamable HTTP:

• http://db.dnaerys.org:80/mcp
• https://db.dnaerys.org:443/mcp

For local build with stdio transport see details below

Architecture

MCP Server is implemented as a Java EE service, accessing 1KGP dataset via gRPC calls to public Dnaerys variant store service.

• service implementation is based on Quarkus MCP Server
• provides MCP over Streamable HTTP, HTTP/SSE and STDIO transports

Examples

Answers below are from Sonnet 4.5: some from multi-agent Research system, some with extended thinking mode, and some from a single-agent system in normal mode.

Identify potential modifier variants for well-known pathogenic alleles in TTN - variants that consistently co-occur in the same haplotype block with pathogenic alleles and may alter severity or penetrance. Conduct research for pathogenic alleles documented in the literature. Use KGP dataset of healthy individuals to find potential modifier variants. Start with 100kb for "the same haplotype block" definition, then extend if required. Evaluate statistical significance for the best modifier candidates found. No initial constraints for modifier types.

• it feels a bit unreal how easily this thing can pull not entirely nonsensical events from a dataset with p = 2.29×10⁻¹³... which makes one wonder what else is possible with a proper study design, specialised disease and control cohorts, and a bit more dedication
• same task for KCNH2, SCN5A, CACNA1C, LMNA, SPAST and BMPR2

or

Which regions in POLR2A are most likely disease-critical, with strong purifying selection, based on available variation patterns across functional domains in KGP ? Do statistical evaluation.

• results for CACNA1A (chart), SCN1A, SCN2A (chart), POLR2A (chart), RPL5 (interactive vis), RPL11, RPS26

or

In what cardiac related genes, e.g. ion channels, variants in KGP dataset near catalytic residues or ligand-binding pockets show strong depletion compared to flanking residues (±20 amino acids) ?

• results might be some

or

Are there patterns of variation in KGP dataset that suggest digenic or oligogenic interactions for Bardet-Biedl syndrome ? Check variety of combinations and zygosity patterns.

or

Which variants in the HBB gene are unexpectedly tolerated in the KGP dataset with at least several annotation sources in agreement with regard to their expected pathogenicity ?

or

Rank all rare KGP variants in genes associated with arrhythmia disorder by their expected clinical relevance, not by predicted pathogenicity alone. Find affected individuals with highest clinical priority variants.

• results might be some

Feel free to open a PR with your favorite prompts

Available Tools

Description for 30 tools and parameters can be found here

Installation

Project can be run locally with MCP over stdio transport, so the MCP server can be started as a subprocess by MCP clients (like Claude Desktop or Goose).

• build the project and package it as a single über-jar:
  • jar is located in target/onekgpd-mcp-runner.jar and includes all dependencies

./mvnw clean
./mvnw package -DskipTests -Dquarkus.package.jar.type=uber-jar

• start from MCP client with a full path to the jar file (for stdio transport, default configuration) or run as a separate service with streamable HTTP transport (requires a change in configuration)
  • project expects JRE 21 to be available at runtime

java -jar <full path>/onekgpd-mcp-runner.jar

Usage with Claude Desktop

To use with Claude Desktop, add to claude_desktop_config.json:

{
  "mcpServers": {
    "OneKGPD": {
      "command": "java",
      "args": ["-jar", "/full/path/onekgpd-mcp-runner.jar"]
    }
  }
}

Verification

How many variants exist in 1000 Genome Project ?

License

This project is licensed under the Apache License 2.0 - see the LICENSE file for details.