"Databricks" matching MCP servers:

Enables MCP-compatible clients to execute Databricks CLI commands without shell interpolation, with pipes and redirects stripped so clients can filter or format raw output. It supports any subcommand permitted by the configured Databricks authentication profile.

Enables AI assistants to execute SQL queries and explore databases, tables, and catalogs on Databricks using Unity Catalog.

Read-only MCP server for Databricks, exposing Unity Catalog browsing and SQL execution with robust write protection via SQL AST analysis.

MCP server for Databricks Unity Catalog, enabling table listing, schema description, and read-only SQL query execution via natural language. Built from scratch to demonstrate JSON-RPC 2.0 protocol depth.

Enables managing Databricks directly from Cursor IDE with 30 tools for notebooks, clusters, jobs, DBFS, SQL, and workspace operations.

Enables AI assistants to search and explore Databricks AWS documentation through semantic search and 10 MCP tools.

Enables semantic search over Databricks docs, API reference, Terraform provider docs, and knowledge base via tools like search_databricks_docs and research.

Enables conversational assessment and migration of Domo estates to Databricks, allowing AI clients to discover, analyze, and transpile Domo assets into Databricks pipelines.

This read-only MCP Server allows you to connect to Databricks data from Claude Desktop through CData JDBC Drivers. For full CRUD support, check out the first managed MCP platform: CData Connect AI (https://www.cdata.com/ai/).

Answers natural-language questions against Postgres, Oracle, Snowflake, Databricks, DuckDB and SQLite via db_read(question) and get_schema(), each separately grantable. The model only proposes SQL — shape, access, dialect and query plan are checked deterministically before any rows are read, and the server refuses rather than returning an unverified answer.

Enables AI agents to pre-flight estimate query costs, enforce hard budgets, reconcile actual billed spend, and suggest cheaper rewrites across BigQuery, Snowflake, and Databricks.