MCP.Market

Pkgtruth MCP server

by hxckya·io.github.hxckya/pkgtruth·v0.2.2·4 stars

Catches hallucinated and slopsquatted npm and PyPI packages before an agent installs them.

A89/100grade A
What users say
No reviews yet
Be the first
Safety scan
A89/100

full report

Adoption
Growing

4 stars68 downloads/wk

Reviews

Write one

Nobody has reviewed Pkgtruth yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Pkgtruth tools (3)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • check_dependencies

    Verify many npm or PyPI packages at once — use this before writing a package.json or requirements.txt,

  • check_install_command

    Verify the packages a shell command would install or execute, before running it:

  • check_package

    Verify a single npm or PyPI package before installing, importing, or recommending it.

Public scan report

scanner v0.1.10 · 2026-10-02 · same rubric, same numbers if you re-run it

no findings
  • Code scan13 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 4 days ago15/15
  • Maintainer identityregistry namespace matches repository owner6/10
Overall 89/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Pkgtruth compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
89/100
higher than 83% of 4,460 AI and agents servers
Tools
3
the typical AI and agents server has 6
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
4
more than 77% of 2,711 AI and agents servers
Downloads a week
68
more than 53% of 1,538 AI and agents servers with a package

What its tools let an agent do: 3 read

Install Pkgtruth in Claude Code, Cursor or VS Code

Runs npx -y pkgtruth on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add pkgtruth -- npx -y pkgtruth
Add to Cursor

What the publisher says

From the Pkgtruth repository's README, as published. We do not edit it. Read it on GitHub

pkgtruth

Ground truth about npm and PyPI packages, for AI coding agents and CI.

Your agent just wrote npm install unused-imports. That package is not the linter plugin it meant. It is a name an attacker registered because models kept inventing it — and npm has since replaced it with a security placeholder.

pkgtruth catches that before it reaches your lockfile — as an MCP server the agent asks, a CLI for CI, a GitHub Action on pull requests, or a Claude Code hook that denies the install command itself.

Why this exists

Large language models invent package names. Measured across models, 19.7% of generated package names were hallucinated, and when researchers re-ran the prompts, 43% of those names came back every single time.

That reproducibility is the whole attack. An attacker does not need to compromise a maintainer, poison a build server, or find a vulnerability. They watch what models invent, register the name, and wait. The technique is called slopsquatting, and it is already happening in the wild.

The standing security advice is that agents with package-management capabilities should not install anything without a review gate. pkgtruth is that gate, in a form an agent can call on its own.

Found in the wild

Two names a model plausibly produces, both live on npm today:

types-node is what you get when a model drops the scope from @types/node. npm removed it for malicious code in December 2024 and it is still installed ten times a week.

socket-io is not malicious — it is an abandoned package with a confusable name. That it takes 1,486 installs a week anyway is the point: a dot and a hyphen are enough.

PyPI has the same shape without the placeholder:

Neither is spelled anything like the package it stands in for, which is why pkgtruth also reads what a deprecation notice says: when it names a far more popular package, that name is the evidence.

npx pkgtruth check types-node socket-io
npx pkgtruth check -e pypi sklearn pytorch

Those two came from a hand check of twenty names. The systematic version — 242 well-known packages, every plausible garbling of each, regenerated every Monday — lives in SLOPSQUATS.md. Section A there is npm security placeholders alone: names npm purged for malware that are still being installed this week. Weeks in which names enter or leave the list are published as releases, so the releases feed is a way to follow the live list without watching the repository.

Install

As an MCP server (for coding agents)

{
  "mcpServers": {
    "pkgtruth": {
      "command": "npx",
      "args": ["-y", "pkgtruth"]
    }
  }
}

Three tools become available:

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Pkgtruth: common questions

Is Pkgtruth MCP server safe?
Yes, by our scan: it is graded A (89/100). Read the Pkgtruth safety report
How do I install Pkgtruth?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Pkgtruth need an API key?
No secret keys are declared. It reads 4 settings from the environment.
Is Pkgtruth maintained?
The last commit was 37 days ago (2026-09-28). The latest release is v0.2.2.
What can I use instead of Pkgtruth?
Servers from other publishers that do the same job: Decionis MCP server, TradeOS (test) MCP server and Agent Security Scanner MCP server.
How does Pkgtruth compare with other AI and agents MCP servers?
safety score 89/100 (higher than 83% of 4,460 AI and agents servers); tools 3 (the typical AI and agents server has 6); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Pkgtruth

Same job from other publishers: the closest match first, then the best rated.

  • Decionis
    Authorize consequential AI agent actions before execution
    A
  • TradeOS (test)
    [TEST] TradeOS MCP bridge: ticker search, My Agent, chart TA, macro news. npm or HTTP.
    C
  • Agent Security Scanner
    Security layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities.
    C