Skip to content

PkgGuard

by youraitools.co · remote · local (npm) · no sign-in to list tools · v0.1.1 · published by co.youraitools

Dependency scan for agents: known CVEs and malicious packages via OSV.dev. By Crypto Money Maker

Changes · 2

2 tools: 2 change things.

Scanned Oct 22, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http pkgguard https://api.youraitools.co/pkgguard/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

2 tools

Changes things 2Claude Code: ask
  • check_packageChecks one package version (npm, PyPI, Go, crates.io, Packagist, RubyGems, Maven, NuGet) against OSV.dev.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Checks one package version (npm, PyPI, Go, crates.io, Packagist, RubyGems, Maven, NuGet) against OSV.dev. Free preview tier: verdict and advisory count. The paid x402 endpoint /v1/package adds advisory ids, severity, CVSS and fixed-in versions.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
    • idempotentHint: true
  • scan_dependenciesChecks a package.json, lockfile, requirements.txt, go.mod, Cargo.lock, poetry.lock or composer.lock (or a list of packages) against OSV.dev for known vulnerabilities and confirmed-…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Checks a package.json, lockfile, requirements.txt, go.mod, Cargo.lock, poetry.lock or composer.lock (or a list of packages) against OSV.dev for known vulnerabilities and confirmed-malicious packages. Free preview tier: verdict and counts, up to 25 packages. The paid x402 endpoint /v1/scan adds per-package advisory ids, severity, CVSS and fixed-in versions (up to 500 packages).

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
    • idempotentHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 0.1.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http pkgguard https://api.youraitools.co/pkgguard/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__pkgguard__scan_dependencies",
      "mcp__pkgguard__check_package"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as pkgguard. Review it before you use it.