mcp-maven-deps

audit_project_dependencies

Read-only

Scan build files to find outdated dependencies, known vulnerabilities, and license issues. Filter to only flagged results to reduce output on large projects.

Instructions

Orchestrates a full dependency audit: scans project build files, checks for available updates, and optionally queries OSV.dev for vulnerabilities. Optional includeLicenses adds license categorization, summary, and newLicenseCategories (categories unique in the scanned set). Optional onlyIssues narrows the returned dependencies to only those with a signal (error, available upgrade, vulnerability, or license flag); summary always covers the full scanned set.

Input Schema

TableJSON Schema

Name	Required	Description
`onlyIssues`	No	Return only dependencies with a signal (error, upgrade available, vulnerability, or license flag) plus a compact summary. Default false (unchanged full output). Reduces response size on large projects.
`projectPath`	No	Project root used to resolve declared repositories. Defaults to the current working directory.
`productionOnly`	No	Exclude test-scope dependencies (default true)
`includeLicenses`	No	Include license intelligence (POM/GitHub resolve + category summary). Default false to avoid extra POM fetches.
`includeVulnerabilities`	No	Include OSV vulnerability check (default true)

Output Schema

TableJSON Schema

Name	Required	Description	Default
`summary`	Yes
`buildSystem`	Yes
`dependencies`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.1.0Oct 6, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations only declare readOnlyHint and openWorldHint; the description adds substantive behavioral context beyond them, including the external OSV.dev query, the license categorization side effect, and the fact that onlyIssues filters dependencies while the summary still covers the full scanned set. It omits cost/latency characteristics of the network-heavy stages.

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?

Three dense sentences, front-loaded with the orchestration summary before the optional flags. Every clause carries information, though the third sentence is long and stacks two flag behaviors into one breath.

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?

With an output schema present and 100% schema coverage, the description need only cover orchestration and flag interactions, which it does. It stops short of noting network/auth implications or that stages can partially fail, but nothing essential for correct invocation 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 baseline is 3, but the description goes further by defining the meaning of includeLicenses output (newLicenseCategories as categories unique in the scanned set) and clarifying onlyIssues semantics relative to the summary. That is real added meaning beyond the schema text.

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?

The description names a specific verb and resource and enumerates the orchestrated steps: build-file scan, update check, optional OSV.dev vulnerability query. It is clearly a composite/full-audit tool, but it never contrasts itself with the close sibling scan_project_dependencies, so an agent must infer the difference.

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

Usage Guidelines3/5

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

Usage is implied by the framing as a 'full dependency audit' with optional stages, and the flag descriptions hint at cost tradeoffs. However, there is no explicit when-to-use-this-vs-alternative guidance and none of the many granular siblings (check_multiple_dependencies, get_dependency_vulnerabilities, scan_project_dependencies) are referenced.

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