discover-tools

Discover Databricks UC functions, Vector Search indexes, Genie spaces, and MCP endpoints.

Updated May 10, 2026
One-click install
npx skills add https://github.com/keqingli1129/agent-langgraph-one --skill discover-tools-keqingli1129
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: discover-tools
Source: https://github.com/keqingli1129/agent-langgraph-one/tree/main/.claude/skills/discover-tools
Command: npx skills add https://github.com/keqingli1129/agent-langgraph-one --skill discover-tools-keqingli1129

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Finding the right Databricks assets (like UC functions, Vector Search indexes, or Genie spaces) can stall development when you do not know what is available in your workspace.

Core Features & Use Cases

  • Pre-build discovery: Run a dedicated discovery step before writing agent code to reduce guesswork and integration churn.
  • Workspace-aware inventory: Identify tool candidates across UC functions, Vector Search indexes, Genie spaces, and MCP endpoints.
  • Targeted scoping: Focus discovery by catalog/schema, select output formats, and generate reports for team review.

Quick Start

Run the discover-tools command to generate a report of available UC functions, Vector Search indexes, Genie spaces, and MCP endpoints in your Databricks workspace.

Frequently Asked Questions about discover-tools

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

FAQPage Schema
How do I discover available Databricks Unity Catalog functions and Vector Search indexes before writing agent code?

To discover Databricks Unity Catalog functions and Vector Search indexes, you can run a dedicated discovery step using the discover-tools command to generate an inventory report of available workspace assets. This ensures you know exactly what resources exist before you start coding.

What is the best way to list all Genie spaces and MCP server endpoints in my Databricks workspace?

The best way to list Genie spaces and MCP server endpoints is to run an automated discovery process that scans your Databricks workspace. This generates a comprehensive report of both custom and external MCP endpoints alongside other available tools.

Can I filter Databricks tool discovery results by specific catalog and schema?

Yes, you can filter Databricks tool discovery results by catalog and schema. When running the discovery command, you can apply optional catalog and schema filtering to focus the output on specific scopes within your workspace.

Does the Databricks tool discovery process support JSON and markdown output formats?

Yes, the Databricks tool discovery process supports both JSON and markdown output formats. You can select your preferred output format to easily generate reports for team review or integrate the results into downstream systems.

How do I run a pre-coding planning check for Databricks agent integration readiness?

To run a pre-coding planning check for agent integration readiness, execute the discovery command via uv run discover-tools. This identifies UC functions, Vector Search indexes, Genie spaces, and MCP endpoints to reduce integration churn.

What Databricks resource types are included in a workspace tool discovery scan?

A workspace tool discovery scan includes Unity Catalog functions, Vector Search indexes, Genie spaces, and both custom and external MCP server endpoints. This covers the primary resource types needed for agent integration.