kbase-query

Query and explore KBase BERDL Datalake databases and tables via MCP REST.

44|13|Updated Nov 15, 2025
One-click install
npx skills add https://github.com/openscientist-io/openscientist --skill kbase-query
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: kbase-query
Source: https://github.com/openscientist-io/openscientist/tree/main/skills/domain/berkeley-data-lakehouse/kbase-query
Command: npx skills add https://github.com/openscientist-io/openscientist --skill kbase-query

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires curl, jq, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Enables researchers and data scientists to programmatically access and interrogate the KBase BERDL Datalake via MCP REST API, turning raw dataset indices into actionable insights.

Core Features & Use Cases

  • Discover and explore available databases and tables in the KBase BERDL Datalake.
  • Retrieve table schemas, sample data, and execute SQL-like queries against the lake.
  • Use cases include data discovery for bioinformatics workflows, reproducible data retrieval, and rapid prototyping of data-driven hypotheses.

Quick Start

Ask it to list databases, then list tables for a database, and optionally run a query against a table.

Frequently Asked Questions about kbase-query

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I query the KBase BERDL Datalake via MCP REST?

You query the KBase BERDL Datalake by using Python requests to POST to MCP endpoints such as /delta/databases/list and /delta/tables/query, allowing you to discover databases, tables, and schemas.

Do I need a KBASE_TOKEN to access KBase datasets programmatically?

Yes, accessing KBase datasets programmatically requires a KBASE_TOKEN environment variable and an MCP URL to authenticate and execute requests against the datalake endpoints.

What dependencies are required to explore KBase datalake schemas and tables?

Exploring KBase datalake schemas and tables requires curl and jq installed, which facilitate HTTP requests and JSON parsing when interacting with the MCP REST API.

Can I run SQL queries against the KBase BERDL Datalake for bioinformatics workflows?

Yes, you can execute SQL-like queries against the KBase BERDL Datalake to retrieve sample data and schemas, supporting data discovery and reproducible retrieval in bioinformatics workflows.

How do I list available databases and tables in the KBase BERDL Datalake?

You list available databases and tables by sequentially calling MCP REST endpoints, starting with listing databases, then requesting the tables for a specific database to explore its structure.

What are the limitations of using MCP REST for KBase datalake discovery?

The MCP REST approach for KBase datalake discovery is limited to programmatic access via Python requests and requires manual endpoint configuration, making it suited for rapid prototyping rather than automated pipeline scaling.