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.
What it does
Summarized from README ↗Gives agents Databricks Unity Catalog metadata (catalogs, schemas, tables, columns, lineage) and lets them run SQL.
Key capabilities
- List catalogs and schemas
- Table details with columns and lineage
execute_sql_query- Long-running query handling
More Databricks servers
custom-mcp-databricks-app
databricks-solutions · Databricks
Template for hosting your own MCP prompts and tools on Databricks Apps with OAuth. You write tools as Python functions with the Databricks SDK.
Databricks managed MCP servers (Genie One, SQL, AI Search, UC functions)
Databricks · Databricks
Databricks-provided MCPs in the system.ai schema, governed through Unity Catalog. No hosting needed.
mcp-databricks-server
JordiNeil · Databricks
Lets LLMs run SQL on Databricks SQL warehouses and list and check Databricks jobs.
databricks-genie-mcp
alexxx-db · Databricks
Exposes the Databricks Genie API as tools for natural language querying of Databricks data.