Built on Quarkus MCP Server framework to provide natural language access to the 1000 Genomes Project dataset, enabling variant, sample, and genotype queries with filtering by annotations, coordinates, zygosity, and inheritance models across 138 million variants and 3202 samples.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@OneKGPdshow me pathogenic variants in SCN5A with ClinVar annotations"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
1000 Genomes Project Dataset MCP Server
Real time access to 1000 Genomes Project dataset, hosted online in Dnaerys variant store
Sequenced & aligned by New York Genome Center (GRCh38). 3202 samples: 2504 unrelated samples from phase three panel + 698 samples from 602 family trios (dataset details)
Key Features
real-time access to 138 044 723 unique variants and ~442 billion individual genotypes
variant, sample and genotype selection based on coordinates, annotations, zygosity
filtering by VEP (impact, biotype, feature type, variant class, consequences), ClinVar Clinical Significance (202502), gnomADe + gnomADg 4.1, AlphaMissense Score & AlphaMissense Class annotations
filtering by inheritance model (de novo, heterozygous dominant, homozygous recessive)
returned variants annotated with HGVSp, gnomADe + gnomADg, AlphaMissense score + cohort-wide statistics
Online Service
Remote MCP service via Streamable HTTP:
http://db.dnaerys.org:80/mcp
https://db.dnaerys.org:443/mcp
Architecture
Implemented as a Java EE service, accessing KGP dataset via gRPC calls to public Dnaerys variant store service.
provides MCP over Streamable HTTP, HTTP/SSE and STDIO transports
service implementation is based on Quarkus MCP Server framework
Available Tools
MCP tools and parameters are here
Installation
Project can be run locally with MCP over stdio and/or http transports
Option A - build & run locally
build the project and package it as a single über-jar:
jar is located in
target/onekgpd-mcp-runner.jarand includes all dependencies
run it locally with dev profile
both stdio and http transports are enabled
http transport is on quarkus http.port
project expects JRE 21 to be available at runtime
Option B - build & run in docker
in order to run in docker, stdio transport needs to be disabled to prevent application from stopping itself due to closed stdio in containers
it's already configured in prod profile
it's the default configuration overall
build with prod profile
run as you prefer, e.g.
Option C - pull from Docker Hub
pull prebuilt image; stdio transport disabled, http transport on port 9000
run
Connecting with MCP clients
to connect via http transport, remote or local, simply direct the client to a destination, e.g.
http://localhost:9000/mcporhttps://db.dnaerys.org:443/mcpto connect via stdio transport, MCP client should start application with dev profile and with a full path to the jar file
e.g. add to Claude config files (e.g.
claude_desktop_config.json):
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.