dbx-mcp

Supervisor (multi-agent) agents

manage_mas

Destructive

Create, update, and delete Databricks Supervisor Agents, their tools, examples, and permissions via a safety-checked API.

Instructions

Manage Supervisor Agents (Agent Bricks multi-agent orchestrators that route to Genie spaces, Knowledge Assistants, UC functions, UC connections (MCP), apps and volumes).

Actions:

list / get / delete; create (spec: display_name, description, instructions); update (spec fields).
list_tools / get_tool / delete_tool; add_tool (tool_id + spec: tool_type, description and the matching block, e.g. {'tool_type':'genie_space','genie_space':{'id':'...'},'description':'...'} or {'tool_type':'knowledge_assistant','knowledge_assistant':{'knowledge_assistant_id':'...'}}); update_tool (only description can change).
list_examples / get_example / add_example (spec: question, guidelines) / update_example / delete_example.
get_permissions / update_permissions (spec: access_control_list). Query a supervisor through its serving endpoint (manage_serving_endpoint action=query).

Safety classification: list, get, list_tools, get_tool, list_examples, get_example = READ_ONLY; create, update, add_tool, update_tool, add_example, update_example = WRITE; delete, delete_tool, delete_example = DESTRUCTIVE; 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.
`tool_id`	No	Tool id (add_tool: the id to assign; others: id or full resource name).
`page_size`	No	Max items to return (server caps this).
`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.
`supervisor_agent_id`	No	Supervisor Agent id or resource name 'supervisor-agents/{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

A4.5/5.0

Behavior5/5

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

Goes well beyond the coarse annotations (readOnlyHint=false, destructiveHint=true, openWorldHint=true) by classifying each individual action as READ_ONLY, WRITE, DESTRUCTIVE, or SECURITY_SENSITIVE, so an agent knows exactly which action triggers confirmation. It also discloses the constraint that update_tool can only change the description, a real behavioral limit not present in annotations.

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?

Front-loaded with the resource definition, then grouped into action families with terse bullets and a compact safety line. Slightly long for a description, but the density is justified by 17 actions; little is wasted.

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

Completeness4/5

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

For a composite multi-action tool with an output schema and 100% schema coverage, the description covers action semantics, spec shape, and the confirmation/destructive flow (confirm, dry_run interplay implied). It does not spell out the confirmation workflow in full, but the schema's confirm field carries that.

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, but the description adds concrete spec payload examples (e.g. {'tool_type':'genie_space','genie_space':{'id':'...'}}) that the generic schema field ('Request body fields...') does not provide. It also clarifies that update_mask defaults to spec keys and that unknown fields are rejected.

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?

Starts with a specific verb+resource ('Manage Supervisor Agents') and immediately defines what a Supervisor Agent is (a multi-agent orchestrator routing to Genie spaces, KAs, UC functions/connections, apps, volumes), which sharply distinguishes it from siblings like manage_genie and manage_ka. The per-action breakdown makes the scope unambiguous.

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?

Enumerates all 17 actions with the spec fields each requires, and routes querying to the sibling 'manage_serving_endpoint action=query', which is genuinely useful cross-tool guidance. It lacks explicit when-not-to-use guidance (e.g. when to pick manage_ka over add_tool), so it falls short of a 5.

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

Deploy Server