databricks-mcp-server
If you are the rightful owner of databricks-mcp-server and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
A Model Context Protocol (MCP) server for interacting with Databricks.
The Databricks MCP Server is a specialized server designed to facilitate interaction with Databricks workspaces through the Model Context Protocol (MCP). It provides a structured interface for managing and querying data within Databricks, making it easier for developers and data scientists to work with large datasets and complex queries. The server supports various functionalities such as listing catalogs, schemas, and tables, executing SQL queries, and managing SQL warehouses. It is compatible with multiple platforms including Linux, Windows, and macOS, and integrates seamlessly with development environments like VS Code. The server uses Databricks unified authentication for secure access and can be easily installed and configured using standard package management tools.
Features
- Lists all catalogs available in the Databricks workspace.
- Lists all schemas in a specified Databricks catalog.
- Lists all tables in a specified Databricks schema with optional filtering.
- Executes SQL statements on a Databricks SQL warehouse and returns the results.
- Lists all SQL warehouses available in the Databricks workspace.
Tools
list_catalogs
Lists all catalogs available in the Databricks workspace.
list_schemas
Lists all schemas in a specified Databricks catalog.
list_tables
Lists all tables in a specified Databricks schema with optional filtering.
execute_sql
Executes SQL statements on a Databricks SQL warehouse and returns the results.
list_warehouses
Lists all SQL warehouses available in the Databricks workspace.