PatternStack
Provides crowdsourced package intelligence and security alerts for AI coding assistants by analyzing project dependencies and framework co-occurrence. It enables automated project scans, package alternative discovery, and data-driven recommendations across multiple programming ecosystems.
README
🪸 @patternstack/mcp
PatternStack MCP Server - Crowdsourced package intelligence for AI coding assistants. Like Waze, but for your dependencies.
Features
- 🔮 Automatic Insights - Zero prompting required. Insights surface as you code.
- 🔍 Framework Detection - Scans package files to detect your tech stack
- 🛤️ Crowdsourced Data - See what real projects use together
- 🔒 Security Alerts - CVE warnings via Dependabot/GitHub Advisory Database
- ⚡ Always Current - 30-day half-life ensures fresh, relevant data
Quick Start
npx -y @patternstack/mcp patternstack-v4
Setup
1. Get Your API Key
Visit patternstack.ai/dashboard/keys and generate an API key.
2. Add to Your MCP Config
Claude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"patternstack": {
"command": "npx",
"args": ["-y", "@patternstack/mcp", "patternstack-v4"],
"env": {
"PATTERNSTACK_API_KEY": "your-api-key-here"
}
}
}
}
Workspace API keys: add your user ID so PatternStack can verify workspace membership on each request:
{
"mcpServers": {
"patternstack": {
"command": "npx",
"args": ["-y", "@patternstack/mcp", "patternstack-v4"],
"env": {
"PATTERNSTACK_API_KEY": "ps_ws_...",
"PATTERNSTACK_CLERK_USER_ID": "user_..."
}
}
}
}
Claude Code (~/.claude/settings.json):
{
"mcpServers": {
"patternstack": {
"command": "npx",
"args": ["-y", "@patternstack/mcp", "patternstack-v4"],
"env": {
"PATTERNSTACK_API_KEY": "your-api-key-here"
}
}
}
}
3. Run init
After restarting your AI assistant, type:
init
This verifies your API key, detects your tech stack, and confirms everything is working.
API Key Configuration
The MCP client looks for API keys in this order (first found wins):
| Priority | Source | Description |
|---|---|---|
| 1 | Environment Variable | PATTERNSTACK_API_KEY in MCP config |
| 2 | .patternstack file |
JSON file in project root: { "apiKey": "..." } |
| 3 | .env file |
PATTERNSTACK_API_KEY=... in project .env |
| 4 | Global config | ~/.patternstackrc with { "apiKey": "..." } |
Free includes full MCP access: Free accounts get full MCP access with 500 requests/day. Workspace (1,000/day) and Premium (5,000/day) tiers offer higher limits for teams.
Workspace keys require a user ID: set PATTERNSTACK_CLERK_USER_ID (or PATTERNSTACK_USER_ID) in your MCP config env so PatternStack can verify you’re still an active workspace member.
Best Practice: Use environment variable in MCP config for security. Never commit API keys to version control.
MCP Tools
| Tool | Description | Tier |
|---|---|---|
init |
Initialize PatternStack, validate API key, auto-discover config | Workspace+ |
scan_project |
Full scan with framework detection, security, and recommendations | Workspace+ |
patternstack_analyze |
Quick local analysis without persisting | Workspace+ |
patternstack_alternatives |
Find alternatives to a package with adoption stats | Workspace+ |
patternstack_security |
Check for security vulnerabilities | Workspace+ |
patternstack_trends |
Get trending packages in an ecosystem | Workspace+ |
patternstack_insights |
Get suggestions Claude should offer you (collaborative) | Workspace+ |
search_packages |
Search packages by name or category with trend/health data | Workspace+ |
compare_packages |
Compare multiple packages with scores and recommendations | Workspace+ |
migration_guide |
Get migration guidance for deprecated/declining packages | Premium |
ai_insight |
AI-powered package explanations and recommendations | Premium |
Note: Framework parameters only accept Tier 1 application frameworks (Next.js, Django, Rails, etc.), not UI libraries (React, Vue). For React projects, use next, remix, or gatsby as the framework.
How It Works
Real Projects → Package Files → Co-occurrence Counts → Temporal Weighting → Recommendations
(Empirical) (Crowdsourced) (Time-decay) (Data-driven)
No AI/ML - Pure statistics from real project data:
PackageCooccurrencetable stores actual counts from real projects- 30-day half-life decay weights recent data more heavily
- Adoption rates are real:
count / totalProjectsWithA
Supported Ecosystems
- JavaScript/TypeScript (npm)
- Python (PyPI)
- Go (go.mod)
- Rust (Cargo)
- Ruby (Bundler)
- PHP (Composer)
- Elixir (Hex)
- Java/Kotlin (Maven)
- C#/.NET (NuGet)
- Dart/Flutter (Pub)
- Swift (SwiftPM)
Development
cd packages/mcp-server
npm install
npm run build
npm run dev
License
MIT
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。