Databricks

Provides an MCP interface to interact with Databricks workspaces, enabling catalog, schema, table queries and SQL execution.

go

4

GitHub Stars

go

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "characat0-databricks-mcp-server": {
      "command": "./databricks-mcp-server",
      "args": []
    }
  }
}

You run the Databricks MCP Server to interact with Databricks workspaces through the Model Context Protocol (MCP). It exposes tools to list catalogs, schemas, tables, SQL warehouses, and to execute SQL against a Databricks SQL warehouse, enabling streamlined data exploration and integration via MCP clients.

How to use

You connect an MCP client to the Databricks MCP Server to perform common data source operations. Use the provided tools to navigate catalogs, schemas, and tables, list available SQL warehouses, and run SQL statements against a Databricks SQL warehouse. Each tool returns structured data that you can consume in your application or workflow.

How to install

Prerequisites: Ensure you have Go 1.24 or later installed.

Download the latest release for your platform from the Releases page.

Start the MCP server by running the following command in your terminal.

./databricks-mcp-server

Notes and useful tips

The server uses Databricks unified authentication. Configure authentication as needed to access your Databricks workspace.

If you want to run the server locally, start it from the directory where the binary or script is located. The server listens for MCP protocol commands on standard input/output.

Available 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.