Schema | databricks-mcp

databricks-mcp

Describes the environment variables required to run the server.

Name	Required	Description	Default
`MAX_ROWS`	No	Maximum number of rows any query may return. Default is 1000.	1000
`DB_BACKEND`	No	Backend to use: 'duckdb' or 'databricks'. Default is 'duckdb'.	duckdb
`DATABRICKS_TOKEN`	No	Databricks personal access token (required when DB_BACKEND=databricks).
`DATABRICKS_HTTP_PATH`	No	Databricks HTTP path (required when DB_BACKEND=databricks). E.g. /sql/1.0/warehouses/abc123
`DATABRICKS_SERVER_HOSTNAME`	No	Databricks server hostname (required when DB_BACKEND=databricks). E.g. dbc-xxxxxxxx-xxxx.cloud.databricks.com

Features and capabilities supported by this server

Capability	Details
`tools`	{ "listChanged": false }
`prompts`	{ "listChanged": false }
`resources`	{ "subscribe": false, "listChanged": false }
`experimental`	{}

Functions exposed to the LLM to take actions

Name	Description
list_tablesA	List the tables available in the warehouse with their column counts.
describe_tableB	Return columns, types, and row count for a table.
sample_rowsB	Return up to `n` (max 100) preview rows from a table.
run_sqlA	Run a read-only SELECT query. DDL/DML/multi-statement queries are rejected; a row LIMIT is enforced automatically.
profile_tableA	Return per-column null fraction, distinct count, and min/max for a table.

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/openatlaspro-AI/databricks-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server