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
๐ชธ @patternstack/mcp
PatternStack MCP Server - Crowdsourced package intelligence for AI coding assistants. Like Waze, but for your dependencies.
Features
- ๐ฎ Automatic Insights - Zero prompting required. Insights surface as you code.
- ๐ Framework Detection - Scans package files to detect your tech stack
- ๐ค๏ธ Crowdsourced Data - See what real projects use together
- ๐ Security Alerts - CVE warnings via Dependabot/GitHub Advisory Database
- โก 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 youโre 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 โ Package Files โ Co-occurrence Counts โ Temporal Weighting โ 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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
E2B
Using MCP to run code via e2b.