Databricks AI Dev Kit

Databricks AI Dev Kit is an open-source toolkit designed to supercharge AI-driven development (vibe coding) on Databricks by providing coding assistants like Claude Code, Cursor, Windsurf, and Gemini CLI with the trusted sources they need. It includes a Python core library, an MCP server with 50+ tools, 20 markdown skills teaching Databricks patterns, and a full-stack Visual Builder App. The kit enables developers to build Spark Declarative Pipelines, Databricks Jobs, AI/BI Dashboards, Unity Catalog assets, RAG-based Knowledge Assistants, MLflow Experiments, Model Serving endpoints, and Databricks Apps.

• MCP Server — Exposes 50+ executable tools for AI assistants via the Model Context Protocol, enabling direct interaction with Databricks resources.
• Databricks Skills — 20 markdown skill files teaching Databricks patterns and best practices, installable into Claude Code, Cursor, Gemini CLI, and Genie Code.
• Core Python Library (databricks-tools-core) — High-level Python functions for SQL execution, pipeline management, and more; compatible with LangChain, OpenAI Agents SDK, and any Python framework.
• Visual Builder App — A full-stack web application with a chat UI for Databricks development, powered by Claude Code integration.
• Genie Code Skills — Install skills directly into your Databricks workspace for use in Genie Code's natural language data exploration UI.
• Multi-tool Support — Works with Claude Code, Cursor, Gemini CLI, Antigravity, and GitHub Copilot via a single install script for Mac, Linux, and Windows.
• Quick Install — Get started with a single bash or PowerShell command; supports project-level and global installation scopes.
• Proactive Dependency Security — Continuously monitors the dependency tree against known vulnerabilities and supply chain advisories.