dbx-mcp

Manage Databricks Apps

manage_app

Destructive

Create, deploy, start, stop, update, or delete Databricks Apps; inspect apps and deployments, with confirmations for destructive actions.

Instructions

Manage Databricks Apps. Actions: create (name, app fields, no_compute), get, list, update (partial: only the given app fields), delete, deploy (source_code_path, mode SNAPSHOT|AUTO_SYNC, extra deployment fields), get_deployment, list_deployments, start, stop. create/deploy/start/stop return immediately with status 'pending' unless wait=true (bounded). logs is not available via the API/SDK. Created apps are tracked in the project manifest.

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

Input Schema

TableJSON Schema

Name	Required	Description
`app`	No	create/update: App fields (REST names), e.g. description, resources, compute_size, user_api_scopes, budget_policy_id. update changes only the fields given.
`mode`	No	deploy: SNAPSHOT (copy source now) or AUTO_SYNC (keep syncing from source_code_path).
`name`	No	App name (lowercase letters, numbers, hyphens).
`wait`	No	Wait (bounded) for the operation to reach a steady state.
`action`	Yes	create \| get \| list \| update \| delete \| deploy \| get_deployment \| list_deployments \| start \| stop \| logs
`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).
`deployment`	No	deploy: extra AppDeployment fields (e.g. git_source, command, env_vars).
`no_compute`	No	create: do not start app compute after creation.
`page_token`	No	next_page_token from a previous response.
`deployment_id`	No	get_deployment: deployment id.
`timeout_seconds`	No	Max seconds to wait when wait=true (capped by DBX_MCP_MAX_WAIT_SECONDS).
`source_code_path`	No	deploy: workspace folder with the app source, e.g. /Workspace/Users/me/app.

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

A4.3/5.0

Behavior4/5

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

Annotations already flag destructiveHint=true/openWorld, but the description adds real value beyond them: safety level varies by action (DESTRUCTIVE/EXECUTION/READ_ONLY/SECURITY_SENSITIVE/WRITE), create/deploy/start/stop return 'pending' unless wait=true (bounded), `logs` is unavailable, and created apps are tracked in the manifest. Return format is left to the output schema, which exists.

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 purpose, then a scannable action list, then behavioral notes. Dense but every clause carries signal (async semantics, partial-update semantics, safety variance); only mildly verbose overall.

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?

Given an output schema exists, return values need not be described, and the description covers actions, async/wait behavior, and per-action safety. The confirmation/dry_run flow is delegated to the schema, which is acceptable but leaves a little room.

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 meaningful action-to-parameter mapping (e.g. deploy = source_code_path + mode SNAPSHOT|AUTO_SYNC, update = partial fields) that orients the agent before reading the schema.

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?

States a specific verb+resource (manage Databricks Apps) and enumerates the full action set, so the agent knows exactly the operation surface without opening the schema. The name and scope cleanly separate it from sibling manage_* tools targeting clusters, warehouses, jobs, etc.

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?

Maps each action to its relevant inputs (create takes name/app/no_compute, deploy takes source_code_path/mode, etc.), which gives clear invocation context. It does not, however, explicitly route between siblings or state when-not-to-use, so it stops 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