RafaelCartenet/mcp-databricks-server

Model Context Protocol (MCP) server for Databricks that empowers AI agents to autonomously interact with Unity Catalog metadata. Enables data discovery, lineage analysis, and intelligent SQL execution. Agents explore catalogs/schemas/tables, understand relationships, discover notebooks/jobs, and execute queries - greatly reducing ad-hoc query time.

52
/ 100
Established

Implements MCP protocol with stdio transport to expose Databricks SQL execution and UC metadata as LLM-callable tools in Markdown format, enabling agents to iteratively explore catalogs, analyze code-level lineage (notebooks/jobs), and construct queries without human intervention. Integrates with Claude, Cursor, and other MCP-compatible AI frameworks via standardized tool calling. Leverages UC descriptions and column-level documentation to reduce query ambiguity while supporting long-running query management and Terraform-based metadata-as-code workflows.

No Package No Dependents
Maintenance 10 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

36

Forks

20

Language

Python

License

MIT

Last pushed

Jan 27, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/mcp/RafaelCartenet/mcp-databricks-server"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.