PatternStack
Uses Clerk user IDs to verify workspace membership for secure access to PatternStack tools and higher request limits.
Provides crowdsourced package intelligence, trends, and health data for PHP projects using the Composer ecosystem.
Offers package recommendations, adoption statistics, and health data for Dart projects using Pub.
Surfaces security alerts and CVE warnings by integrating with Dependabot and the GitHub Advisory Database.
Detects Django as a target framework to provide context-aware package insights and collaborative recommendations.
Provides package intelligence, co-occurrence data, and ecosystem trends for Elixir projects using Hex.
Offers package insights and adoption statistics specifically for Flutter applications using the Pub ecosystem.
Identifies Gatsby projects to surface relevant crowdsourced package recommendations and health data.
Leverages the GitHub Advisory Database to provide security vulnerability alerts and package health assessments.
Analyzes JavaScript project files to provide package health data, alternatives, and collaborative insights via npm.
Supports package analysis, security scanning, and ecosystem trends for Kotlin projects using Maven.
Provides package intelligence, adoption statistics, and health data for C# and .NET projects using NuGet.
Detects Next.js as a Tier 1 application framework to provide tailored package insights and trending suggestions.
Scans npm package files to detect tech stacks and provide crowdsourced intelligence from real-world projects.
Analyzes NuGet dependencies to provide trending package data, scores, and migration guidance for deprecated packages.
Provides crowdsourced package intelligence and security alerts for PHP applications using the Composer ecosystem.
Analyzes PyPI packages to surface trends, health data, and alternatives for Python projects.
Detects Python tech stacks and provides data-driven package recommendations based on real-world co-occurrence.
Identifies Remix projects to provide framework-specific package intelligence and collaborative insights.
Supports dependency analysis, package health insights, and security warnings for Ruby projects using Bundler.
Provides package intelligence and security warnings for Rust projects using the Cargo ecosystem.
Offers package insights, health data, and adoption statistics for Swift projects using SwiftPM.
Analyzes TypeScript projects to offer crowdsourced package intelligence, trends, and alternative suggestions via npm.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@PatternStackscan my project for security vulnerabilities and package recommendations"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
🪸 @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-v4Setup
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:
initThis 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 |
|
2 |
| JSON file in project root: |
3 |
|
|
4 | Global config |
|
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 |
| Initialize PatternStack, validate API key, auto-discover config | Workspace+ |
| Full scan with framework detection, security, and recommendations | Workspace+ |
| Quick local analysis without persisting | Workspace+ |
| Find alternatives to a package with adoption stats | Workspace+ |
| Check for security vulnerabilities | Workspace+ |
| Get trending packages in an ecosystem | Workspace+ |
| Get suggestions Claude should offer you (collaborative) | Workspace+ |
| Search packages by name or category with trend/health data | Workspace+ |
| Compare multiple packages with scores and recommendations | Workspace+ |
| Get migration guidance for deprecated/declining packages | Premium |
| 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 projects30-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 devLicense
MIT
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/patternstack-ai/mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server