Onekgp MCP

🚀 1000 Genomes Project dataset MCP Server

This project offers natural language access to the 1000 Genomes Project dataset, which is hosted online in the Dnaerys variant store. The dataset was sequenced and aligned to GRCh38 by the New York Genome Center. It includes 2504 unrelated samples from the phase three panel and an additional 698 samples related to those in the 2504 - sample panel, totaling 3202 samples (1598 males and 1604 females). You can find dataset details here.

🚀 Quick Start

The remote MCP service is accessible online via Streamable HTTP:

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

For local build with stdio transport, refer to details below.

✨ Features

• Real - time access: Gain real - time access to 138 044 724 unique variants and about 442 billion individual genotypes in 3202 samples.
• Selection based on multiple criteria: Select variants, samples, and genotypes based on coordinates, annotations, and zygosity.
• Annotation - based filtering: Filter by VEP, ClinVar, gnomAD AF, and AlphaMissense annotations.
• Inheritance model filtering: Filter by inheritance model (de novo, heterozygous dominant, homozygous recessive).

📦 Installation

The project can be run locally with MCP over stdio transport. The MCP server can be started as a subprocess by MCP clients (such as Claude Desktop or Goose).

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

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

2. Start from the 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). The project expects JRE 21 to be available at runtime.

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

Usage with Claude Desktop

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

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

Verification

How many variants exist in 1000 Genome Project?

💻 Usage Examples

Try analytical or open - ended questions to leverage the analytical strength of LLMs, for example:

Basic Usage

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.

• Results might be some (Sonnet 4.5)

Advanced Usage

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 (Sonnet 4.5)

You can also try other questions like:

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.

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?

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 (Sonnet 4.5)

Feel free to open a PR with your favorite prompts.

📚 Documentation

The description for 30 tools and parameters can be found here.

🔧 Technical Details

The MCP Server is implemented as a Java EE service, accessing the 1KGP dataset via gRPC API calls to the public Dnaerys variant store service with the 1000 Genomes dataset hosted online.

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

📄 License

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