packrun
npm for agents and humans
Packrun is an MCP server that enables AI coding assistants to search, compare, and analyze npm packages using real-time metrics and automated scoring. It provides seven tools for querying package metadata, checking health status, finding alternatives, and comparing packages across 50+ categories like HTTP clients, date libraries, and ORMs. The server is hosted at mcp.packrun.dev/mcp and integrates with Cursor, Claude Desktop, and other MCP-compatible clients. Package scoring combines download trends, bundle size, freshness, community engagement, and code quality into 0-100 ratings to help agents recommend optimal dependencies.
Key Features
Use Cases
- 01AI agents helping developers choose between competing npm packages like axios vs. got vs. ky
- 02Automated dependency recommendations during code generation based on bundle size and maintenance status
- 03Finding modern alternatives to deprecated or outdated packages like moment.js
- 04Validating package compatibility before AI-suggested installations to prevent conflicts
- 05Comparing entire categories of packages such as testing frameworks or state management libraries
- 06Retrieving real-time health metrics to assess whether a package is actively maintained
Related MCP Servers
View moremarkitdown
Python tool for converting files and office documents to Markdown.
firecrawl
The context API to search, scrape, and interact with the web at scale. 🔥
prompts.chat
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
langflow
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
packrun — FAQ
What is the Packrun MCP server?+
Packrun is an MCP server that provides AI coding assistants with tools to search, compare, and analyze npm packages using real-time metrics and automated scoring across 50+ categories. It helps agents recommend optimal JavaScript dependencies based on downloads, bundle size, freshness, and code quality.
How do I connect Packrun to Cursor or Claude Desktop?+
Add the server configuration to your MCP settings JSON file with the hosted endpoint: {"mcpServers": {"packrun": {"url": "https://mcp.packrun.dev/mcp"}}}. No local installation, API keys, or additional setup is required since the server is hosted.
Which AI clients work with Packrun?+
Packrun works with any MCP-compatible client including Cursor, Claude Desktop, and other assistants that support the Model Context Protocol.
Do I need API keys or prerequisites to use Packrun?+
No API keys or prerequisites are required for the hosted MCP server. Simply add the endpoint URL to your client configuration and the server is ready to use.
Is Packrun free to use?+
Yes, Packrun is open source under the MIT license and the hosted MCP endpoint is available for free. The project is maintained at github.com/midday-ai/packrun.
What tools does the Packrun MCP server provide?+
The server provides seven tools: search_packages, get_package, get_package_health, compare_packages, find_alternatives, get_comparison_category, list_comparison_categories, and validate_install for comprehensive npm package analysis.
How do I install packrun?+
Open the source repository on GitHub and follow its README. packrun is a mcp server — MCP Agents Market links you directly to the official repo.
Is packrun free?+
packrun is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.