What is the KBase Query skill used for?

It allows Claude Code users to query the KBase/BERDL biological data lake directly, enabling data discovery and SQL-based analysis of microbiome and genomic datasets.

What kind of data is available through this skill?

The data lake includes pangenomic data with GTDB taxonomy, NMDC microbiome core data, KBase genome collections, and UniProt reference data.

Does this skill require any external tools?

Yes, the skill requires the 'jq' utility to be installed on your local system to process and format the JSON responses from the KBase API.

Can I run complex SQL queries?

Yes, the skill supports full SQL syntax for querying databases, though results are typically limited to 1,000 rows for optimal performance.

Do I need an authentication token to use this skill?

Yes, you need a KBase Auth Token obtained from the KBase JupyterHub to authenticate requests to the MCP REST API.

KBase Datalake Query

Name: KBase Datalake Query
Author: cmungall

bycmungall

0•

Ciencia de Datos y ML

Enables seamless SQL querying and exploration of biological data within the KBase/BERDL data lake via MCP.

KBase Query is a specialized skill designed for researchers and bioinformaticians working with large-scale biological datasets. It provides a direct interface to the KBase/BERDL Datalake, allowing users to discover databases like kbase_ke_pangenome and nmdc_core, inspect table schemas, and execute complex SQL queries. By integrating the KBase Model Context Protocol (MCP) server, this skill streamlines the process of exploring pangenomic data, GTDB taxonomy, and microbiome metadata directly within a Claude Code workflow, eliminating the need to manually toggle between data portals and development environments.

Características Principales

01Execute SQL queries against biological and microbiome data lakes

02List available databases including NMDC core and pangenomic collections

03Integrated support for processing large JSON outputs with jq

04Explore database structures and retrieve detailed table schemas

05Sample rows from massive datasets for rapid data validation

060 GitHub stars

Casos de Uso

01Analyzing NMDC microbiome metadata to identify specific environmental samples

02Querying GTDB taxonomy and pangenomic data for comparative genomics

03Extracting UniProt reference data subsets for local analysis pipelines

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add cmungall/lakehouse-skills kbase-query

For use in Claude.ai and ChatGPT

Download Skill