dbx-mcp

Manage volume files

manage_volume_files

Destructive

List, read, upload, download, delete, and create files or directories in Unity Catalog Volumes, with path validation and confirmation for destructive actions.

Instructions

Unity Catalog Volume file operations: list, get_metadata, upload (inline content / content_base64, or local_path; overwrite replaces an existing file and is DESTRUCTIVE), download (returned inline up to DBX_MCP_MAX_INLINE_DOWNLOAD_BYTES - as text when UTF-8, else base64 - or saved to local_path), delete (file), delete_directory (empty dirs; recursive deletes contents after confirmation), create_directory. Paths are validated against traversal and the configured volume allowlist.

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

Input Schema

TableJSON Schema

Name	Required	Description
`path`	Yes	Volume path: /Volumes/<catalog>/<schema>/<volume>/...
`action`	Yes	list: directory entries; get_metadata: file (or directory) metadata; upload: write a file; download: read a file; delete: delete a file; delete_directory: delete a directory (recursive=true deletes its contents too); create_directory: create a directory (and parents).
`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.
`content`	No	upload: UTF-8 text content.
`dry_run`	No	If true, validate and return the planned change without executing it.
`overwrite`	No	upload: replace an existing file (DESTRUCTIVE; requires confirm).
`page_size`	No	Max items to return (server caps this).
`recursive`	No	delete_directory: also delete all files and sub-directories inside it.
`local_path`	No	upload: source file / download: destination file, relative to DBX_MCP_LOCAL_FILE_ROOT (local file access is disabled unless that is set).
`page_token`	No	next_page_token from a previous response.
`content_base64`	No	upload: binary content, base64-encoded.

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

Behavior5/5

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

Despite annotations already flagging destructiveHint=true, the description adds substantial context the annotations cannot: the confirm/'confirmation_required' workflow, path validation against traversal and a volume allowlist, the DESTRUCTIVE nature of overwrite, the inline download byte cap with UTF-8-vs-base64 behavior, and that local file access is disabled unless an env var is set.

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

Conciseness5/5

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

Front-loaded with the resource and scope, then walks the action list and closes with the safety classification. It is dense but every clause carries distinct operational information; nothing is filler for an 11-parameter, 7-action tool.

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?

With an output schema present, return values needn't be described, and annotations plus description together cover the safety profile, the confirm flow, per-action semantics, and path validation. Nothing an agent needs to call this 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 the schema already documents all 11 parameters and the baseline is 3. The description still adds connective meaning the schema lacks: it groups upload sources (content / content_base64 / local_path), ties overwrite to DESTRUCTIVE+confirm, and explains download's local_path vs inline behavior.

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

Purpose4/5

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

Opens with a specific verb+resource ('Unity Catalog Volume file operations') and enumerates every supported action, so an agent knows exactly what domain this covers. However, it never explicitly distinguishes itself from nearby siblings like get_volume_folder_details or manage_workspace_files, leaving that routing to inference.

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?

Each action carries a parenthetical that clarifies its scope (delete_directory for empty dirs, recursive deletes contents after confirmation, create_directory creates parents), which effectively tells the agent when to pick each. What's missing is any exclusion or alternative-tool guidance versus the file-related siblings.

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

Deploy Server