How do I install mcp-databricks-server?

Its README did not state an install command plainly enough for us to quote one, so we do not guess. The repository has the instructions: https://github.com/RafaelCartenet/mcp-databricks-server

What does mcp-databricks-server connect to, and what does it need?

It reaches databricks. The credentials we found in its source are DATABRICKS_TOKEN.

Is mcp-databricks-server official and is it maintained?

We found nothing naming it as a vendor’s official server. Its repository has 43 GitHub stars and its state in our directory is listed. Its last commit we recorded was on 2026-03-28.

What licence does mcp-databricks-server use?

The repository declares the MIT licence.

InfratoApp / Resources / MCP servers / mcp-databricks-server

mcp-databricks-server

mcp-databricks-server is an MCP server, listed under databases. It reaches databricks. It needs DATABRICKS_TOKEN to authenticate. Its repository has 43 GitHub stars and is licensed under MIT; we last read it on 2026-10-23.

This server integrates Model Context Protocol (MCP) with Databricks, allowing AI agents to interact with Unity Catalog metadata. It supports data discovery, lineage analysis, and intelligent SQL execution.

Install

MCP servers are packaged differently from each other -- some run via npx, some as a Docker image, some as a plain script you clone and run. mcp-databricks-server’s own README did not state one plainly enough for this page to quote it rather than guess, so it will not guess. The repository below states it.

Read mcp-databricks-server’s own install instructions ↗

What it reaches, and what it needs

Reaches

databricks

Credential

DATABRICKS_TOKEN

What it connects to

Wraps

Databricks

Unverified means a mention in the server’s own description, not a citation. A wrong claim here costs nothing to correct and nothing to trust yet.

Maintenance

Stars

State

listed

Licence

MIT

From the repository

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.

View on GitHub ↗2026-10-23

What mcp-databricks-server can do

5 tools documented in its README. An AI client calls these by name.

list_uc_catalogs: Lists all available Unity Catalogs with their names, descriptions, and types.
describe_uc_catalog: Provides a summary of a specific Unity Catalog, listing all its schemas with their names and descriptions.
describe_uc_schema: Provides detailed information about a specific schema within a Unity Catalog. Returns all tables in the schema, optionally including their column details.
describe_uc_table: Provides a detailed description of a specific Unity Catalog table with comprehensive lineage capabilities.
execute_sql_query: Executes a given SQL query against the Databricks SQL warehouse and returns the formatted results.

Read from the README; names are kept only if the README contains them.