MCP server · Developer tools

whichlib MCP server

Ask your AI which library to use and get a scored, compared answer from GitHub instead of a guess.

Developer tools For it and development Developer Tools

whichlib helps your AI pick a library when you are about to add one to a project. Instead of trusting a guess, it looks up real GitHub repos and gives each one a score from 0 to 100 with a short verdict. It is handy for anyone who codes with an AI assistant and wants a second opinion before installing something.

What is an MCP server? The 30-second version

On its own, your AI can only chat from what it already knows. An MCP server is a small helper program that gives your AI a new skill or a connection to a service. This helper connects your AI to GitHub, so it can search for libraries and check how active and popular they are. When you ask which library to use, the AI uses this helper to look things up and answer with real data instead of a guess.

What this MCP server does

You ask your AI something like which library to use for reading PDFs in Python. The AI passes that need to whichlib, which searches GitHub for matching repositories. whichlib scores each one on momentum, maintenance, adoption and license, then writes a one-line verdict. The AI reads that back to you as a short ranked list so you can pick with more confidence.

What you can do with it

Get a ranked list of libraries for a need you describe in plain words
Compare two to ten GitHub repos side by side
See the top starred repos created today, this week or this month
Check a repo's score, tier and one-line verdict before installing it
Filter results by language like Python or TypeScript
See npm or PyPI download numbers where they are known
Spot archived or very new repos you should be careful about

Try asking your AI

“Which Python library should I use to parse PDFs?”
“Compare axios and got for making HTTP requests in Node”
“Show me the most starred repos created this week in Rust”
“Is this library still maintained or has the project gone quiet?”

What it gives back to you

You get a short ranked list of repositories, each with a score from 0 to 100, a tier such as Strong or Watch, and a one-line verdict. You also see the four subscores, any warning flags, and npm or PyPI download numbers when they are known. It all shows up as normal text in the chat, with the details available as structured data behind the scenes.

Before you start

What you need

Node.js 22 or newer if you install it yourself
The Claude desktop app or another AI client that supports MCP servers
A GitHub token is optional and only raises the request limit (a kind of password for apps; a no-permission token is enough)

Good to know

The scores are a helpful guide, not the final word, and very new repos are marked as too new to judge, so double-check before you commit to a library.

Install it with your AI

Add whichlib MCP server to your AI, no technical skills needed

You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.

Sign in to get the install prompt

Members get a ready-made prompt that lets the Claude desktop app check whichlib MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,609 MCP servers here for you.