原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。评价和账户功能将在后续阶段推出。
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚

Pkgverdict

作者:CloudCorpRecords版本 0.1.1i★ –i在你的电脑上运行
注册名称io.github.CloudCorpRecords/pkgverdict

安装

概览

作者提供的说明(英文原文)

Pre-install verdicts for npm packages: GO, RISKY, FAKE, or MISSING. Built for humans and AI agents.

PopNx MCP 的三大支柱

这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。

它能帮你做什么

我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。

  • 连接方式: 在你的电脑上运行
  • 传输方式: stdio
  • 分类: 其他

安装

选择你使用的 AI 应用,然后复制设置。

安装之前

  • 基础检查:1 项中通过 1 项
  • 在你的电脑上运行,拥有你的用户账户的权限(文件、网络、应用)。
  • 注册中心没有列出需要填写的密钥。

你需要

你用的是哪个应用?

在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。

打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json

{
  "mcpServers": {
    "pkgverdict": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/cloudcorprecords/pkgverdict:0.1.1",
        "mcp"
      ]
    }
  }
}

在终端中运行这条命令

claude mcp add pkgverdict -- docker run -i --rm ghcr.io/cloudcorprecords/pkgverdict:0.1.1 mcp

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "pkgverdict": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/cloudcorprecords/pkgverdict:0.1.1",
        "mcp"
      ]
    }
  }
}

浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "pkgverdict": {
      "type": "stdio",
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/cloudcorprecords/pkgverdict:0.1.1",
        "mcp"
      ]
    }
  }
}

浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。

这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。

你的选择通过 Cookie 保存在这台设备上,无需账户。

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。

它能做什么

它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。

基础检查i

我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月6日

  • ✓ 通过

    作者与仓库一致

    注册名称已通过 GitHub 账户 CloudCorpRecords 验证,该账户拥有此仓库

  • … 尚未检查

    仍在维护

    我们还没有从 GitHub 读取这个仓库

  • … 尚未检查

    有许可证

    我们还没有从 GitHub 读取这个仓库

  • – 不适用

    端点有响应

    它在你的电脑上运行,没有互联网端点

  • – 不适用

    使用 OAuth 登录

    在你的电脑上运行,改用本地设置

  • … 尚未检查

    工具描述中没有隐藏指令

    它在你的电脑上运行;我们只能读取互联网端点的工具列表

与“其他”中的其他服务器比较i

  • 星标数多于此分类中其他 32461 个服务器的 0%
  • 发布到注册中心的时间比此分类中其他 32461 个服务器的 72% 更新
  • 基础检查结果等于或优于此分类中其他 32461 个服务器的 100%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。

常见问题

Pkgverdict 安全吗?

它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。

它需要哪些密钥或代码?

注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。

它在我的电脑上运行还是在云端?

它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。

它还在维护吗?

GitHub 仓库最后更新于–,最新版本(0.1.1)于14天前进入注册中心。

哪些应用可以使用它?

支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Docker。

有什么可以替代它?

同一分类中有:Spec Driven Development, Remote Desktop Commander, dotnet-mcp

替代选择

同一分类中其他作者的服务器,按星标数排序。

如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

Spec Driven Development

作者:formulahendry

MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.

在你的电脑上运行★ 440MIT14个月前更新
安装

Remote Desktop Commander

作者:desktop-commander

Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.

在云端运行★ 211昨天更新
安装

dotnet-mcp

作者:Skymly

MCP server for .NET symbols, XAML, source generators, and restricted workspace edit

在你的电脑上运行今天更新
安装

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

pkgverdict

Check an npm package before you install it. One command, one verdict: GO, RISKY, FAKE, or MISSING — in plain words your AI coding agent can read too.

pkgverdict ships as a container image on GHCR (there is no npm package named pkgverdict, so npx pkgverdict will 404 — use Docker):

docker run --rm ghcr.io/cloudcorprecords/pkgverdict check react-markdown

[GO] react-markdown@10.1.0

- 5y old, 38.4M/wk, no install scripts, no advisories, no lookalike name.

docker run --rm ghcr.io/cloudcorprecords/pkgverdict check unused-imports

[FAKE] unused-imports@0.0.1-security

- Flagged malicious: MAL-2025-48781. Do not install.

- Name rides on eslint-plugin-unused-imports (suffix of popular name) and the

package is barely downloaded — the classic typosquat shape.

docker run --rm ghcr.io/cloudcorprecords/pkgverdict check react-super-hooks-plus

[MISSING] react-super-hooks-plus

- react-super-hooks-plus is not on the npm registry. If an AI assistant

suggested it, the name was hallucinated.

Why

AI assistants now pick half the packages developers install — and they hallucinate names attackers have already registered (slopsquatting), while typosquats and hijacked releases keep shipping postinstall malware. npm audit only sees published advisories, after the fact. pkgverdict checks before the install: existence, lookalike names, package age, install scripts, maintainers, downloads, and OSV advisories.

Use it inside your AI coding tool

One command sets it up. In your project directory, run:

docker run --rm -v "$PWD":/work -w /work ghcr.io/cloudcorprecords/pkgverdict init --agent claude-code

That installs the MCP server config plus the instruction snippet teaching your agent the one behavior rule: check pkgverdict before installing. Supported tools: claude-code, cursor, copilot (VS Code), windsurf, cline, and generic (init --list shows them all; --all sets up everything; --dry-run previews without writing). Restart your tool, verify with a "list your MCP tools" prompt, and the pkgverdict server should appear with 2 tools (check_package, scan_dependencies). The underlying pack lives in integrations/ if you prefer to install by hand.

CLI

# Verdict on one package (name or name@version)

docker run --rm ghcr.io/cloudcorprecords/pkgverdict check lodash

Check every dependency in package.json, worst first

docker run --rm -v "$PWD":/work -w /work ghcr.io/cloudcorprecords/pkgverdict scan docker run --rm -v "$PWD":/work -w /work ghcr.io/cloudcorprecords/pkgverdict scan ./my-app --no-dev

Check your setup (Node version, registry + OSV reachability, cache)

docker run --rm ghcr.io/cloudcorprecords/pkgverdict doctor

JSON output for scripting and CI

docker run --rm ghcr.io/cloudcorprecords/pkgverdict check left-pad --json

Exit codes: 0 when everything is GO (or RISKY without --strict), 1 when a FAKE or MISSING package is found, 2 on usage errors. For CI gates that should fail on anything suspicious: pkgverdict scan --strict.

Verdicts

VerdictMeaning
GOEstablished package, no red flags. Install away.
RISKYCaution: install scripts, very young, obscure, deprecated, no repo/license, known advisories, or a lookalike name on an otherwise fine package. Read before installing.
FAKELooks actively bad: typosquat-shaped name on a new/obscure package, hostile install script, or a malicious advisory (MAL- id, a MAL- alias, or an OSV record whose details mark the package itself malicious/backdoored — e.g. the event-stream@3.3.6 compromise, carried under a GHSA id). Do not install.
MISSINGNot on the registry at all — a typo or a hallucinated name, with a "did you mean" suggestion when one fits.

Signals come from the npm registry (metadata, downloads), the OSV database (advisories), and a bundled list of well-known packages for lookalike detection. Responses cache under ~/.cache/pkgverdict (6h metadata, 1h advisories); delete that directory to force fresh checks.

Distribution

pkgverdict has exactly two distribution channels, and both are intentional:

  1. GHCR: the container image ghcr.io/cloudcorprecords/pkgverdict, built and pushed by the Publish container workflow on each release.
  2. The MCP Registry: the listing io.github.CloudCorpRecords/pkgverdict, whose server.json carries an OCI package only, pointing at that same GHCR image.

There is no npm package, and that is the model, not a missing step. npx pkgverdict returning 404 is expected. The unscoped name in package.json exists to build the image and version the CLI; the package is marked private so a stray npm publish from a checkout fails fast instead of claiming the name, and the old template workflow that ran npm publish on every release now sits disabled at .github/workflows/publish.yml, printing this model instead of publishing. Publishing to npm later would be a maintainer decision needing a scoped name and a token with rights to it. These facts are pinned by test/distribution.test.ts, so the residue cannot quietly come back.

Run it with Docker

The GHCR image is the primary distribution: ghcr.io/cloudcorprecords/pkgverdict.

Use it as a stdio MCP server:

docker run --rm -i ghcr.io/cloudcorprecords/pkgverdict

Any CLI command can be passed after the image name instead of the default mcp argument:

docker run --rm ghcr.io/cloudcorprecords/pkgverdict <command> [args]

MCP server

Point your MCP client at Docker (stdio):

{

"mcpServers": { "pkgverdict": { "command": "docker", "args": ["run", "--rm", "-i", "ghcr.io/cloudcorprecords/pkgverdict", "mcp"] } } }

Two tools: check_package (verdict on one package) and scan_dependencies (worst-first verdicts for a project's package.json).

Development

npm install

npm run build npm test # offline fixture corpus: every verdict rule pinned to a case

License

MIT.

问 PopNx