MCP Databricks Server MCP Server

Databricks Unity Catalog (UC) allows for detailed documentation of your data assets, including catalogs, schemas, tables, and columns. Documenting

Local serverstdioPython

What is the MCP Databricks Server MCP server?

Most AI and media services work still happens through a UI a human drives. MCP Databricks Server MCP server moves it into the conversation instead. Databricks Unity Catalog (UC) allows for detailed documentation of your data assets, including catalogs, schemas, tables, and columns. Documenting these assets thoroughly requires an investment of time. One common question is: what are the.

The short version

This Model Context Protocol (MCP) server is designed to interact with Databricks, with a strong focus on leveraging Unity Catalog (UC) metadata and enabling comprehensive data lineage exploration. The primary goal is to equip an AI agent with a comprehensive set of tools, enabling it to become independent in answering questions about your data. By autonomously exploring UC, understanding data structures, analyzing data lineage (including notebook and job dependencies), and executing SQL queries, the agent can fulfill data requests without direct human intervention for each step.

The tools it exposes

The server publishes 8 tools. What each one is for:

  • LLM — Focused Output**: All descriptive tools return information in Markdown format, optimized for consumption by Large Language Models, making it easier
  • Description — Lists all available Unity Catalogs with their names, descriptions, and types
  • Args — * catalog_name: The name of the Unity Catalog to describe (e.g., prod, dev, system)
  • schema_name — The name of the schema to describe
  • include_columns — If True, lists tables with their columns. Defaults to False for a briefer summary
  • include_lineage — Set to True to fetch comprehensive lineage (tables, notebooks, jobs). Defaults to False. May take longer to retrieve but provides rich context for
  • Note — This is the same tool listed under "Core Capabilities" but is repeated here in the context of a typical agent workflow involving UC exploration
  • Installation — Create a .env file in the root directory of this project with your Databricks credentials:

Getting it running

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.

What it needs from you

Configuration is passed through the environment: DATABRICKS_HOST, DATABRICKS_TOKEN, DATABRICKS_SQL_WAREHOUSE_ID. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

How it compares

This sits in the AI and media services group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. MCP Databricks Server's toolset — LLM, Description, Args and 5 more — is a fair guide to whether it matches your workflow. It is maintained by RafaelCartenet; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
LLMFocused Output**: All descriptive tools return information in Markdown format, optimized for consumption by Large Language Models, making it easier for agents to parse and understand the context.
DescriptionLists all available Unity Catalogs with their names, descriptions, and types.
Args* catalog_name: The name of the Unity Catalog to describe (e.g., prod, dev, system).
schema_nameThe name of the schema to describe.
include_columnsIf True, lists tables with their columns. Defaults to False for a briefer summary.
include_lineageSet to True to fetch comprehensive lineage (tables, notebooks, jobs). Defaults to False. May take longer to retrieve but provides rich context for understanding data dependencies and enabling code exploration.
NoteThis is the same tool listed under "Core Capabilities" but is repeated here in the context of a typical agent workflow involving UC exploration followed by querying.
InstallationCreate a .env file in the root directory of this project with your Databricks credentials:

How to install the MCP Databricks Server MCP server

Example using `python`:
```json
{
    "mcpServers": {
        "databricks": {
            "command": "python",
            "args": [
                "/path/to/your/mcp-databricks-server/main.py"
            ]
        }
    }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
DATABRICKS_HOSTEndpoint or connection string the server talks to.Optional
DATABRICKS_TOKENCredential the server authenticates with.Yes
DATABRICKS_SQL_WAREHOUSE_IDConfiguration value read at startup.Optional

Example prompts to try

  • Use MCP Databricks Server to LLM.
  • Use MCP Databricks Server to Description.
  • Use MCP Databricks Server to Args.

Frequently asked questions

It connects MCP Databricks Server to MCP-compatible AI assistants such as Claude and Cursor, exposing 8 tools (LLM, Description, Args, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with MCP Databricks Server directly.