dbx-mcp

Run and monitor pipelines

manage_pipeline_run

Destructive

Start, stop, and monitor Spark Declarative Pipeline updates, then inspect errors and event logs to troubleshoot failed runs.

Instructions

Run and monitor Spark Declarative Pipeline updates and surface pipeline errors.

start (pipeline_id[, full_refresh, refresh_selection, full_refresh_selection, validate_only, parameters, wait, timeout_seconds]): EXECUTION; returns update_id with status 'pending'. Full refreshes are also DESTRUCTIVE (confirm required) because table state is reset.
stop (pipeline_id): stops the active update (DESTRUCTIVE, confirm required).
get_update / wait (pipeline_id[, update_id] - default latest): state; failed updates include ERROR events.
list_updates (pipeline_id): update history, newest first.
list_events (pipeline_id[, level, update_id, filter]): event log, newest first.

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

Input Schema

TableJSON Schema

Name	Required	Description
`wait`	No	start: poll until the update finishes (bounded).
`level`	No	list_events: only events of this level.
`action`	Yes	start: start an update; stop: stop the active update; get_update: one update's state (+errors if failed); list_updates: update history; list_events: event log (use level='ERROR' for errors); wait: poll an update until it finishes (bounded).
`filter`	No	list_events: raw filter, e.g. "timestamp > '2025-01-01T00:00:00Z'".
`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).
`update_id`	No	get_update/wait (defaults to the latest update); list_events: filter.
`page_token`	No	next_page_token from a previous response.
`parameters`	No	start: key/value pipeline parameters.
`pipeline_id`	Yes	Pipeline id.
`full_refresh`	No	start: reset ALL tables before running (DESTRUCTIVE).
`validate_only`	No	start: only validate the source code; materialize nothing.
`timeout_seconds`	No	Max seconds to wait (capped by server).
`refresh_selection`	No	start: tables to refresh (incremental).
`full_refresh_selection`	No	start: tables to fully refresh (DESTRUCTIVE).

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

Behavior5/5

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

Adds substantial context beyond the annotations: full refreshes are flagged DESTRUCTIVE because table state is reset, stop halts an active update, failed updates carry ERROR events, and start returns status 'pending' with an update_id. It even notes the safety class varies by input, which the readOnly/destructive annotations cannot express.

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 one-line purpose followed by a tight action list and a safety line, with no repeated filler. It is on the longer side for 16 params, but the structure is scannable and each bullet carries distinct information.

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?

An output schema exists, so return values need not be described, and the description covers the branchy action semantics and destructive cases that the flat schema cannot. The only gap is the absence of explicit routing guidance against sibling pipeline tools.

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

Parameters3/5

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

Schema coverage is 100%, so every parameter is already documented, giving the description a baseline of 3. The per-action invocation signatures in the description (e.g., start(...) argument lists) are a mild convenience but do not add syntax or semantics the schema lacks.

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 description states a specific resource (Spark Declarative Pipeline updates) and enumerates exactly the operations it covers via per-action bullets. The distinction from siblings like manage_pipeline (configuration) and manage_job_runs (job runs) is implicit in the resource named, and no sibling covers pipeline run lifecycle.

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 bullets give clear context per action and the safety sentence tells the agent when confirmation is required. It stops short of naming an alternative sibling or stating when NOT to use this tool (e.g., vs manage_pipeline for editing), leaving some routing to inference.

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

Deploy Server