pkg-booper
Provides AI assistants with tools to check npm package versions and security heuristics, including version lookups, signal-based analysis, and batch analysis of package.json files.
README
pkg-booper
Boop your dependencies' snoots.
An MCP server that gives AI assistants tools to check up-to-date npm package versions, as well as gleaning other security heuristics. It's not a super comprehensive analysis, just a lil' snoot boop.
What is this?
pkg-booper is a Model Context Protocol (MCP) server that provides npm package intelligence for AI-assisted development. It fills the gap where documentation tools exist but version/health checking doesn't.
Key features:
- Quick version lookups for any npm package
- Security signal analysis using transparent indicators
- Batch analysis of entire
package.jsonfiles - Caching for fast repeated lookups
Installation
Run directly with npx:
npx pkg-booper
Or install globally:
npm install -g pkg-booper
pkg-booper
MCP Client Configuration
Claude Desktop
Add to your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"pkg-booper": {
"command": "npx",
"args": ["-y", "pkg-booper"]
}
}
}
Cursor
Add to your Cursor MCP settings (.cursor/mcp.json):
{
"mcpServers": {
"pkg-booper": {
"command": "npx",
"args": ["-y", "pkg-booper"]
}
}
}
Claude Code
Add to your Claude Code MCP settings file (.mcp.json):
{
"mcpServers": {
"pkg-booper": {
"command": "npx",
"args": ["-y", "pkg-booper"]
}
}
}
Cline
Add to your Cline MCP settings:
{
"mcpServers": {
"pkg-booper": {
"command": "npx",
"args": ["-y", "pkg-booper"]
}
}
}
Tools
pkg-booper-boop
Quick version lookup for an npm package.
Input:
{
"package": "lodash",
"skipCache": false
}
Output:
{
"success": true,
"package": "lodash",
"latest": "4.17.21",
"tags": {
"latest": "4.17.21"
},
"summary": "lodash@4.17.21"
}
pkg-booper-sniff
Signal-based security analysis of an npm package. Returns information that lets the AI reason about the combination of indicators.
Input:
{
"package": "express",
"version": "4.18.2",
"compareVersions": true,
"skipCache": false
}
Output:
{
"success": true,
"package": "express",
"version": "4.18.2",
"facts": {
"age": { "days": 4500, "created": "2010-12-29" },
"lastPublish": { "days": 180, "version": "4.18.2" },
"weeklyDownloads": 30000000,
"maintainerCount": 3,
"versionCount": 275,
"hasTypes": true,
"hasRepository": true
},
"definitiveIndicators": [],
"behavioralSignals": [],
"info": ["Popular package: 30M weekly downloads"],
"summary": "express@4.18.2: No concerning signals detected"
}
Signal Categories:
definitiveIndicators: Critical security issues (malware markers, deprecated status)behavioralSignals: Patterns that warrant investigation (new package, single maintainer, suspicious scripts)info: Neutral observations (popularity, age, features)
pkg-booper-big-sniff-file
Batch analyze all dependencies from a package.json file.
Input:
{
"path": "/path/to/package.json",
"includeDevDependencies": true,
"skipCache": false
}
Output:
{
"success": true,
"packageJsonPath": "/path/to/package.json",
"results": {
"lodash": { "success": true, "package": "lodash", "..." },
"express": { "success": true, "package": "express", "..." }
},
"summary": {
"total": 15,
"clean": 14,
"suspicious": 1,
"outdated": 3,
"definiteThreats": 0,
"failed": 0
},
"humanSummary": "Analyzed 15 packages: 14 clean, 1 suspicious, 0 threats"
}
pkg-booper-big-sniff-list
Batch analyze a provided list of dependencies.
Input:
{
"dependencies": {
"lodash": "^4.17.21",
"express": "^4.18.2",
"axios": "^1.6.0"
},
"skipCache": false
}
Output: Same format as pkg-booper-big-sniff-file.
pkg-booper-clear-cache
Clear cached npm package data.
Input:
{
"package": "lodash",
"type": "all"
}
package: Optional. Clear cache for specific package, or omit for all.type:"all"|"versions"|"health"|"popular"
Output:
{
"success": true,
"cleared": ["lodash:versions", "lodash:health"],
"summary": "Cleared 2 cache entries for lodash"
}
Configuration
pkg-booper can be configured via YAML files, environment variables, or programmatic overrides.
Configuration File Locations
Files are checked in this order (first found wins):
PKG_BOOPER_CONFIGenvironment variable path./pkg-booper.yaml(project directory)~/.config/pkg-booper/config.yaml(user config)
Example Configuration
# pkg-booper.yaml
cache:
directory: ~/.cache/pkg-booper
ttl: 86400 # 24 hours in seconds
popularPackagesTtl: 604800 # 7 days for popular packages
thresholds:
levenshtein: 2 # Typosquat detection sensitivity
lowDownloads: 100 # Weekly downloads below this trigger a signal
scoring:
weights:
maturity: 0.15
popularity: 0.25
maintenance: 0.25
trust: 0.25
completeness: 0.10
github:
token: ${GITHUB_TOKEN} # Interpolates from environment
timeout: 10000 # Request timeout in ms
rateLimit:
npm:
requestsPerSecond: 10
github:
requestsPerMinute: 30
debug: false
Environment Variables
| Variable | Description | Default |
|---|---|---|
GITHUB_TOKEN |
GitHub API token for enhanced rate limits | - |
PKG_BOOPER_CONFIG |
Path to custom config file | - |
PKG_BOOPER_CACHE_DIR |
Cache directory | ~/.cache/pkg-booper |
PKG_BOOPER_CACHE_TTL |
Cache TTL in seconds | 86400 |
PKG_BOOPER_TIMEOUT |
Request timeout in ms | 10000 |
PKG_BOOPER_DEBUG |
Enable debug logging | false |
Examples
AI Assistant Usage
User: "What's the latest version of React?"
AI uses pkg-booper-boop:
React is currently at version 18.2.0.
User: "Analyze the security of this package.json"
AI uses pkg-booper-big-sniff-file:
I analyzed 23 dependencies:
- 21 packages look clean
- 2 packages have behavioral signals worth noting:
- some-package: New package (< 30 days old), single maintainer
- another-pkg: Significantly outdated (2 major versions behind)
No definitive threats detected, but you may want to review the flagged packages.
User: "Is 'lod-ash' a legit package?"
AI uses pkg-booper-sniff:
Warning: 'lod-ash' appears to be a typosquat of 'lodash':
- Very similar name (Levenshtein distance: 1)
- Much lower download count than lodash
- Created recently compared to lodash
I'd recommend using the official 'lodash' package instead.
License
This is licensed under the AGPLv3.
Why? I feel like information deserves to be free. Code is a sort of information, and I know the AGPL is pretty good at encouraging sharing. That, and I think of the code I put together with the help of generative AI less like an original composition, and more like a silly mashup.
I don't feel comfortable publishing my mashups under anything less open ;)
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。