databricks-agent-bricks

Create and manage Databricks Agent Bricks for knowledge retrieval, SQL exploration, and multi-agent orchestration.

1|Updated Apr 24, 2026
One-click install
npx skills add https://github.com/itsadijmbt/SecureMCP-Servers --skill databricks-agent-bricks-itsadijmbt
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: databricks-agent-bricks
Source: https://github.com/itsadijmbt/SecureMCP-Servers/tree/main/TEST_SERVERS/PORTED_TO_SECUREMCP/databrickslab-mcp/ai-dev-kit/databricks-skills/databricks-agent-bricks
Command: npx skills add https://github.com/itsadijmbt/SecureMCP-Servers --skill databricks-agent-bricks-itsadijmbt

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you quickly build conversational AI capabilities on Databricks by providing ready-to-manage building blocks for document Q&A, SQL exploration, and multi-agent orchestration.

Core Features & Use Cases

  • Create Knowledge Assistants (KA): Enable document-based Q&A using RAG over files stored in Unity Catalog volumes, including guidance for indexing and example creation.
  • Create and use Genie Spaces: Support natural-language-to-SQL workflows using Unity Catalog data exploration tiles.
  • Create Supervisor Agents (MAS): Route user queries to the right specialized agent (KA, Genie space, model-serving endpoints, UC functions, and external MCP servers) using descriptions and routing instructions.

Use case example: Build an enterprise support supervisor that answers policy questions from HR documents (KA), runs analytics questions on usage data (Genie), and performs operational actions like ticket updates through an external MCP server.

Quick Start

Ask the system to create a Knowledge Assistant that indexes your policy PDFs in a given Unity Catalog volume and answers questions with citations to the source documents.

Frequently Asked Questions about databricks-agent-bricks

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

FAQPage Schema
How do I build a Databricks copilot for knowledge retrieval and SQL exploration?

You can build a Databricks copilot by creating Knowledge Assistants for document Q&A over Unity Catalog volumes and wiring Genie Spaces for natural-language-to-SQL data exploration.

How do I set up a multi-agent supervisor on Databricks to route user queries?

You set up a Supervisor Agent to route user queries to specialized agents, model-serving endpoints, Unity Catalog functions, and external MCP servers using routing descriptions and instructions.

Can I use Unity Catalog volumes to create a RAG knowledge assistant on Databricks?

Yes, you can provision a Knowledge Assistant that indexes PDFs and files stored in a Unity Catalog volume to answer questions with citations to the source documents.

Does Databricks agent orchestration support connecting external MCP servers for operational actions?

Yes, Supervisor Agents support routing to external MCP servers, allowing your Databricks copilot to perform operational actions like ticket updates alongside document Q&A and SQL analytics.

What's the best way to combine document Q&A and natural-language SQL in a single Databricks assistant?

Deploy a Supervisor Agent that routes requests between a Knowledge Assistant for policy documents and a Genie Space for usage data analytics, creating a unified enterprise support assistant.

Do I need a specific configuration format to manage Databricks Agent Bricks?

You need a root SKILL.md YAML frontmatter to define configuration for volume paths, agent routing descriptions, and MCP connection references when managing Knowledge Assistants and Supervisor Agents.