dbx-mcp

Knowledge Assistants

manage_ka

Destructive

Create, update, delete, and query Databricks Knowledge Assistants; manage document sources, examples, syncs, and permissions for Q&A over Unity Catalog data.

Instructions

Manage Knowledge Assistants (Agent Bricks document Q&A agents over UC volumes, tables or vector indexes).

Actions:

list / get / delete; create (spec: display_name, description, instructions); update (spec fields among display_name, description, instructions).
list_sources / get_source / delete_source; add_source (spec: display_name, description, source_type 'files'|'index'|'file_table' plus files={path:'/Volumes/...'} or index={index_name,text_col,doc_uri_col} or file_table={table_name,file_col}); update_source (display_name, description); sync_sources re-ingests non-index sources.
list_examples / get_example / add_example (spec: question, guidelines) / update_example / delete_example.
get_permissions / update_permissions (spec: access_control_list). Query an assistant through its serving endpoint (manage_serving_endpoint action=query).

Safety classification: list, get, list_sources, get_source, list_examples, get_example = READ_ONLY; create, update, add_source, update_source, add_example, update_example = WRITE; delete, delete_source, delete_example = DESTRUCTIVE; sync_sources = EXECUTION+WRITE; get_permissions = READ_ONLY+SECURITY_SENSITIVE; update_permissions = SECURITY_SENSITIVE+WRITE.

Input Schema

TableJSON Schema

Name	Required	Description
`spec`	No	Request body fields for create/update, using the Databricks REST API field names (snake_case). Unknown fields are rejected.
`action`	Yes	Operation to perform.
`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.
`page_size`	No	Max items to return (server caps this).
`source_id`	No	Knowledge source id (or full resource name).
`example_id`	No	Example id (or full resource name).
`page_token`	No	next_page_token from a previous response.
`update_mask`	No	Comma-separated fields to update; defaults to the keys present in spec.
`knowledge_assistant_id`	No	Knowledge Assistant id or resource name 'knowledge-assistants/{id}'.

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

A4.4/5.0

Behavior4/5

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

Annotations only give a global destructiveHint=true and openWorldHint=true, which over-warns for the many read actions. The description adds real per-action granularity by classifying each action as READ_ONLY, WRITE, DESTRUCTIVE, EXECUTION+WRITE, or SECURITY_SENSITIVE, and notes that sync_sources re-ingests non-index sources. That is meaningful disclosure beyond the annotations, though it does not describe async timing or failure behavior.

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?

Purpose is front-loaded, actions are grouped as scannable bullets, and the safety classification is one consolidated line rather than repeated per action. It is dense and long, but the density is driven by 18 actions and 10 parameters, and nearly every clause carries actionable information.

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 broad multi-action tool with a rich output schema and fully described parameters, the description supplies the missing pieces: action inventory, per-action payload requirements, safety tiers, and the cross-tool route for querying. Nothing an agent needs to select and invoke an action correctly is absent.

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 the baseline is 3 and the schema alone documents confirm, dry_run, page_size, ids, and update_mask. The description goes beyond that by spelling out the spec payload shape per action (display_name/description/instructions; source_type 'files'|'index'|'file_table' with the nested key names for each), which the generic 'spec' schema object does not convey.

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 gives a specific verb+resource (manage Knowledge Assistants) and immediately characterizes what they are (Agent Bricks document Q&A agents over UC volumes, tables or vector indexes). The action enumeration then maps every sub-operation, and the sibling it is NOT for (querying an assistant) is explicitly routed to manage_serving_endpoint.

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

Usage Guidelines4/5

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

The action list plus per-action spec hints tell the agent which operation to pick and what fields each requires. It also names the alternative for the query path (manage_serving_endpoint action=query). However, there is no explicit when-not guidance for overlapping siblings like manage_vs_index or query_vs_index, so it stops short of full routing guidance.

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

Deploy Server