Agent Kiosk

package_audit

Read-onlyIdempotent

Scan npm, PyPI, or Rust crate packages for known CVEs and deprecation using Google OSV.dev. Provide a package name and optional version or ecosystem to audit security and stable release status.

Instructions

Open-source package & CVE security scanner for coding agents. Checks npm, PyPI, or Rust crates against Google OSV.dev for known security vulnerabilities, deprecation status, and latest stable version.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "name": "<name>"
    },
    "name": "package_audit"
  }
}

Input Schema

Name	Required	Description
`name`	Yes	Package name (e.g., 'lodash', 'express', 'requests', 'tokio')
`version`	No	Optional specific version to audit (defaults to latest version)
`ecosystem`	No	Package registry ecosystem (default: 'npm')

Schema Changelog

Changes observed during successful MCP inspections.

First observedv2.5.0Oct 18, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, openWorld, and non-destructive behavior, so the safety profile is covered. The description adds genuinely useful context beyond that: the external dependency on Google OSV.dev and the specific result categories (vulnerabilities, deprecation status, latest stable version). It does not discuss rate limits or result volume, which keeps it short of a 5.

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?

Two tight sentences with no filler; the core capability is front-loaded and the OSV.dev detail follows. 'for coding agents' is slightly redundant framing but costs little.

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 no output schema, the description helpfully enumerates what comes back (vulnerabilities, deprecation, latest stable version), which is exactly what is missing from structured fields. For a read-only scanner with full schema coverage, the definition is nearly self-sufficient, lacking only notes on result limits or upstream availability.

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 description coverage is 100%, so all three parameters are already documented in the schema, including the ecosystem enum. The description confirms the ecosystem set ('npm, PyPI, or Rust crates') and implicitly describes the version parameter ('latest stable version'), adding marginal value over the structured fields rather than new syntax.

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?

States a specific verb and resource: it scans open-source packages for CVEs, deprecation, and latest version. It also names the ecosystems and the upstream data source (Google OSV.dev), so the agent knows exactly what it does. It does not distinguish itself from the sibling security_audit tool, leaving an ambiguity an agent must resolve on its own.

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 phrase 'for coding agents' and by the ecosystems listed, so an agent can infer this is the right tool when checking a dependency. There is no explicit when-to-use/when-not guidance and no mention of how it relates to the similarly named security_audit sibling.

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