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

Dep Oracle

作者:ertugrulakben版本 1.3.0i★ –i在你的电脑上运行
注册名称io.github.ertugrulakben/dep-oracle

安装

概览

作者提供的说明(英文原文)

Predictive dependency security engine. Trust scores, zombie detection, blast radius analysis.

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: 网络安全

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

  • npm已安装 Node.js(用于 npx 命令)

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": {
    "dep-oracle": {
      "command": "npx",
      "args": [
        "-y",
        "dep-oracle"
      ]
    }
  }
}

在终端中运行这条命令

claude mcp add dep-oracle -- npx -y dep-oracle

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": {
    "dep-oracle": {
      "command": "npx",
      "args": [
        "-y",
        "dep-oracle"
      ]
    }
  }
}

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": {
    "dep-oracle": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "dep-oracle"
      ]
    }
  }
}

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9日

  • ✓ 通过

    作者与仓库一致

    注册名称已通过 GitHub 账户 ertugrulakben 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“网络安全”中的其他服务器比较i

  • 星标数多于此分类中其他 1003 个服务器的 0%
  • 发布到注册中心的时间比此分类中其他 1003 个服务器的 4% 更新
  • 基础检查结果等于或优于此分类中其他 1003 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

Dep Oracle 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(1.3.0)于9个月前进入注册中心。

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 Node.js。

有什么可以替代它?

同一分类中有:Penthera, Draugr, Harbor

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:↓ 每周下载量i★ 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

Penthera

Offline, rule-based security checks for your repo, dependencies, AI agent config and local app.

作者:danoszz起步阶段↓ 1935/周今天更新

在你的电脑上运行

Draugr

Security scanning for AI agents: SAST, SCA, secrets, IaC, DAST, ranked by real risk.

作者:draugr-dev非常新今天更新

在你的电脑上运行✓ draugr.dev

Harbor

Read-only access to Harbor: projects, artifacts, vulnerabilities, robots, replication, agent skills.

作者:oreondev非常新今天更新

在你的电脑上运行

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。

dep-oracle Predictive Dependency Security Engine

Quick Start · Features · Algorithm · MCP · Comparison

English | Turkce


Your dependencies have dependencies. Who's watching them?

dep-oracle is a predictive dependency security engine that calculates Trust Scores (0-100) for every package in your dependency tree. It detects zombie dependencies, measures blast radius, catches typosquatting attempts, and predicts future risks — before they become vulnerabilities.

Claude Code Security scans YOUR code. dep-oracle scans everything your code depends on.

Why?

  • Supply chain attacks increased 742% since 2019 (Sonatype 2024 Report)
  • The average npm project pulls in hundreds of transitive dependencies — any one could be compromised
  • npm audit only catches known CVEs — dep-oracle predicts future risks
  • You audit your code. But do you audit your trust?

Quick Start

# Zero install — just run it

npx dep-oracle

Or install globally

npm install -g dep-oracle dep-oracle scan

Check a single package

dep-oracle check express

Features

FeatureDescription
Trust Score0-100 weighted score per package (security, maintainer health, activity, popularity, funding, license)
Zombie DetectionFinds unmaintained but critical packages (no commits in 12+ months)
Blast RadiusShows how many files are affected if a dependency is compromised
Typosquat Detection1,847+ known packages + live npm registry lookup to catch suspicious names
Trend Prediction3-month risk projection based on download/commit/release trends
Migration Advisor131 package mappings with 192 safer alternatives for risky dependencies
Offline ModeWorks from cache without internet (--offline)
MCP ServerNative Claude Code integration — ask about your dependencies in natural language
Multi-Format OutputTerminal (colored tree), HTML, JSON, and SARIF
GitHub ActionAutomate trust checks in your CI/CD pipeline

Usage

# Scan current project

dep-oracle scan

Scan with specific output format

dep-oracle scan --format json dep-oracle scan --format html dep-oracle scan --format sarif

Check a single package

dep-oracle check lodash dep-oracle check express@4.18.2

Offline mode (uses cached data only)

dep-oracle scan --offline

Set minimum score threshold (exit code 1 if below)

dep-oracle scan --threshold 60

Ignore specific packages

dep-oracle scan --ignore deprecated-but-needed,legacy-pkg

Verbose logging

dep-oracle scan --verbose

Output Example

dep-oracle v1.2.0

Scanning package.json... Found 47 direct dependencies, 683 transitive Collecting data... [=============================] 100% (2.3s)

DEPENDENCY TRUST REPORT ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

CRITICAL (score < 50)

■ event-stream@3.3.6 Score: 12 ZOMBIE Last commit: 2018 | 0 maintainers active Blast radius: 14 files | Alternative: highland

WARNING (score 50-79)

■ moment@2.29.4 Score: 58 ZOMBIE Maintenance mode | No new features Blast radius: 23 files | Alternative: dayjs, date-fns, luxon

SAFE (score 80+): 679 packages

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ SUMMARY Overall Trust Score: 74/100 Critical: 2 | Warning: 3 | Safe: 679 Zombies: 2 | Deprecated: 1

Trust Score Algorithm

Each package is scored 0-100 based on six weighted metrics:

MetricWeightWhat It Measures
Security History25%CVE count with diminishing penalty, average patch time, fast-patch bonus
Maintainer Health25%Active maintainers (bus factor), issue response time, PR merge speed
Activity20%Commit frequency trend, release cadence, last publish recency
Popularity15%Weekly downloads, dependent count, GitHub stars
Funding10%GitHub Sponsors, OpenCollective, corporate backing
License5%MIT/Apache = safe, GPL = risk, Unknown = red flag

Score Ranges: 80-100 Safe | 50-79 Warning | 0-49 Critical

Security Scoring

The security metric uses a diminishing penalty model — the first vulnerability has the highest impact, and each additional one has progressively less effect:

VulnerabilitiesSecurity Score
0100
185
272
360
450
5+max(20, 100 - n*12)

Packages that patch vulnerabilities quickly (within 7 days) receive a +10 bonus. Slower patches (within 30 days) receive +5.

Graceful Degradation

If an API is unreachable (GitHub down, no internet, rate limited), dep-oracle doesn't crash. The missing metric weight is redistributed across available metrics. If 3+ metrics are unavailable, a reliability warning is shown.

Blast Radius Methodology

The blast radius metric counts how many of your source files directly import a given dependency:

  1. Recursively collects all .js, .ts, .jsx, .tsx, .mjs, .mts, .cjs, .cts files
  2. Skips node_modules, .git, dist, build, coverage, and other build directories
  3. Searches each file for import ... from 'pkg', require('pkg'), and dynamic import('pkg') patterns
  4. Reports the count, file paths, and percentage of codebase affected

Current limitations:

  • Only scans JavaScript/TypeScript import patterns
  • Python import statements are not yet analyzed (blast radius returns 0 for Python-only projects)
  • Does not trace re-exports or barrel files — counts direct imports only
Weight Rationale

Weights are based on the principle that security vulnerabilities and maintainer abandonment are the strongest predictors of supply chain risk, followed by development activity signals. Weights are fully configurable via .dep-oraclerc.json — enterprise teams can adjust to match their specific risk tolerance.

When data is unavailable for a metric, the score is pulled toward the midpoint (50) proportionally to the fraction of missing weight, preventing artificial inflation from missing data.

Typosquat Detection

dep-oracle uses a multi-layer approach to catch typosquatting:

  1. Static registry — 1,847+ known popular package names across 40+ categories (React, Vue, Angular, Express, testing, CLI tools, etc.)
  2. Dynamic npm lookup — Fetches the top 5,000 most-downloaded packages from npm and caches them for 7 days
  3. Pattern matching — Levenshtein distance, prefix/suffix manipulation, character swap, missing/extra letter detection
dep-oracle check expresss    # Catches: similar to "express" (distance: 1)

dep-oracle check lodashe # Catches: similar to "lodash" (distance: 1) dep-oracle check react-js # Catches: suffix pattern of "react"

Migration Advisor

When a package scores low or is flagged as a zombie, dep-oracle suggests safer alternatives from a curated database of 131 package mappings with 192 alternatives:

moment     → dayjs, date-fns, luxon

request → axios, got, node-fetch, undici lodash → lodash-es, radash, just (native alternatives) express → fastify, koa, hono gulp → esbuild, tsup, vite mocha → vitest, jest, node:test ...and 125 more

Each suggestion includes difficulty rating (easy/moderate/hard) and migration context.

Claude Code Integration (MCP)

dep-oracle is listed on the official [MCP Registry](https://modelcontextprotocol.io/registry) and works as an MCP server for Claude Code:

// .claude/settings.json

{ "mcpServers": { "dep-oracle": { "command": "npx", "args": ["dep-oracle", "mcp"] } } }

Then in Claude Code, just ask:

  • *"What's the riskiest dependency in this project?"*
  • *"Is lodash safe to use?"*
  • *"Show me zombie dependencies"*
  • *"Suggest alternatives for moment.js"*

Available MCP Tools:

ToolDescription
dep_oracle_scanFull project dependency scan
dep_oracle_trust_scoreTrust score for a single package
dep_oracle_blast_radiusImpact analysis for a package
dep_oracle_zombiesList all zombie dependencies
dep_oracle_suggest_migrationGet alternative package suggestions
dep_oracle_typosquat_checkCheck typosquatting risk for a package name
dep_oracle_compareCompare two packages side-by-side
dep_oracle_reportGenerate a JSON report, optionally to file

GitHub Action

name: Dependency Trust Check

on: [pull_request]

jobs: dep-oracle: runs-on: ubuntu-latest steps:

  • uses: actions/checkout@v4
  • uses: actions/setup-node@v4 with: node-version: '20'
  • name: Run dep-oracle run: npx dep-oracle scan --format sarif --min-score 60 env: GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

Configuration

Create .dep-oraclerc.json in your project root:

{

"threshold": 60, "ignore": ["known-risky-but-needed"], "format": "terminal", "offline": false, "githubToken": "$GITHUB_TOKEN", "cacheTtl": 86400 }

Or add to package.json:

{

"dep-oracle": { "threshold": 60, "ignore": [] } }

Configuration Options
OptionDefaultDescription
threshold60Minimum trust score. Packages below trigger warnings and non-zero exit
ignore[]Packages to skip during scanning
format"terminal"Output format: terminal, json, html, sarif
offlinefalseUse only cached data, skip all API calls
githubTokennullGitHub token for higher API rate limits (5000/hr vs 60/hr)
cacheTtl86400Cache TTL in seconds (default: 24 hours)

Supported Package Managers

ManagerManifestLock FileStatus
npmpackage.jsonpackage-lock.jsonSupported
yarnpackage.jsonyarn.lockSupported
pnpmpackage.jsonpnpm-lock.yamlSupported
piprequirements.txtPipfile.lockSupported
poetrypyproject.tomlpoetry.lockSupported

Comparison

Featurenpm auditDependabotSocket.devSnykdep-oracle
Known CVE scanYesYesYesYesYes
Predictive riskNoNoPartialPartialYes
Trust Score (0-100)NoNoNoNoYes
Zombie detectionNoNoNoNoYes
Blast radiusNoPartialNoNoYes

| Typosquat detection | No | No | Yes | No | **Yes*

只显示了开头部分;其余内容请在仓库中阅读

问 PopNx