dbx-mcp

Manage Unity Catalog objects

manage_uc_objects

Destructive

Create, inspect, list, update, and delete Unity Catalog catalogs, schemas, tables, volumes, and functions for Databricks data governance.

Instructions

Create, inspect, list, update and delete Unity Catalog catalogs, schemas, tables, volumes and functions.

Hierarchy is catalog -> schema -> object: list schemas needs catalog_name; list tables/volumes/functions need catalog_name + schema_name. Identify a target by full_name or by catalog_name/schema_name/name. create/update take spec with Databricks API fields (e.g. catalog: comment, storage_root, properties; volume: volume_type, storage_location, comment; update: comment, owner, new_name, properties). Tables: only EXTERNAL Delta tables can be created via the API (use execute_sql for CREATE TABLE/VIEW); table/function update supports only 'owner'. delete is DESTRUCTIVE; force=true on catalog/schema deletes all contents. Changing owner/isolation_mode is SECURITY_SENSITIVE.

Safety classification: depends on input (DESTRUCTIVE, READ_ONLY, SECURITY_SENSITIVE, WRITE).

Input Schema

TableJSON Schema

Name	Required	Description
`name`	No	Object name relative to its parent (alternative to full_name).
`spec`	No	Request body fields for create/update, using the Databricks REST API field names (snake_case). Unknown fields are rejected.
`force`	No	delete only (catalog/schema/function): drop even if not empty - RECURSIVELY deletes all contents.
`action`	Yes	create \| get \| list \| update \| delete
`confirm`	No	Set to true ONLY after the user has reviewed the plan returned by a previous call with status 'confirmation_required'. Required for destructive/security-sensitive actions.
`dry_run`	No	If true, validate and return the planned change without executing it.
`full_name`	No	Target name: 'catalog', 'catalog.schema' or 'catalog.schema.object' (backticks allowed). For list, may give the parent ('catalog' or 'catalog.schema').
`page_size`	No	Max items to return (server caps this).
`page_token`	No	next_page_token from a previous response.
`object_type`	Yes	catalog \| schema \| table \| volume \| function
`schema_name`	No	Parent schema (required to list tables/volumes/functions).
`catalog_name`	No	Parent catalog (required to list schemas/tables/volumes/functions).

Output Schema

TableJSON Schema

Name	Required	Description	Default
`data`	No
`page`	No
`plan`	No
`tool`	Yes
`action`	No
`safety`	No
`status`	No		success
`summary`	Yes
`warnings`	No
`next_steps`	No	Suggested follow-up calls.
`request_id`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 3, 2026

TDQS

A4.8/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the generic annotations (destructiveHint/openWorldHint/readOnlyHint), the description discloses what gets destroyed (force=true recursively deletes catalog/schema contents), that owner/isolation_mode changes are SECURITY_SENSITIVE, and the confirm-after-confirmation_required workflow. This is meaningful behavioral context the annotations cannot convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Dense but well organized, with the action list front-loaded and the hierarchy/spec/restriction details grouped logically. It is longer than typical, but nearly every sentence carries actionable constraints rather than filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 12-parameter, 5-action, 5-object-type tool, the description covers targeting, hierarchy, spec contents, destructive/sensitive semantics, and the confirmation flow, and an output schema exists to handle return values. Little an agent needs to call it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3, and the description adds real value by listing concrete spec fields per object type (catalog: comment/storage_root/properties; volume: volume_type/storage_location; update: comment/owner/new_name/properties) that the schema only refers to generically. It also clarifies full_name vs catalog_name/schema_name/name targeting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening sentence states a specific set of verbs (create, inspect, list, update, delete) against a specific resource family (Unity Catalog catalogs, schemas, tables, volumes, functions). This clearly separates it from siblings like manage_uc_grants, manage_uc_tags, or manage_uc_storage, which target different UC sub-resources.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives explicit usage conditions: hierarchy requirements for listing (catalog_name for schemas; catalog_name + schema_name for tables/volumes/functions) and the when-not case that only EXTERNAL Delta tables can be created via the API, routing table/view creation to execute_sql instead. It also flags table/function update as owner-only.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server