npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@vovy-ai/mcp-server

v0.3.1

Published

Vovy's MCP server — deterministic project-analysis tools plus the same skill content served as MCP prompts/resources.

Readme

@vovy-ai/mcp-server

The MCP server component of Vovy — a drop-in skill pack for vibe coding safely with AI coding assistants. Free forever, MIT, local-only.

You normally don't install this directly. npx @vovy-ai/go install registers it automatically in your AI coding tool's MCP config (Claude Code, Codex CLI, Cursor, Cline, Windsurf), which then launches it itself via npx -y @vovy-ai/mcp-server.

What it does

  • analyze_project — a deterministic, non-LLM tool: reads package.json and the local file tree to report detected framework/stack, package manager, test runner, and a few concrete security footguns (like an untracked .env). No network access, no guessing, no AI involved.
  • search_codebase — deterministic symbol search over JS/TS/JSX/TSX via @vovy-ai/context-engine: find a symbol's declaration, its usages, a file's structure (including class methods and interface members), or its transitive blast radius (impact: "what breaks if I change this", depth-tagged), without reading whole files. Resolved through your project's own TypeScript when available — so two same-named symbols in different scopes stay distinct — and through tree-sitter otherwise. Every response names which backend answered. No embeddings, no network access.
  • project_memory — records and recalls your project's decisions (with what was rejected and why), mistakes (with how to avoid repeating them), and constraints (with the why behind the rule) as plain markdown under .vovy/memory/, committed to git. Git is the backend: memory travels with clone to every machine, teammate, and AI tool — no account, no server. Recall is deterministic keyword search, and record refuses anything that looks like a credential.
  • Serves the same skill content @vovy-ai/skills ships as MCP prompts and resources (skill://<id>) — a secondary, redundant discovery path alongside the skill files vovy install already writes directly into your tool's native skill directory.

Like the rest of Vovy, this never calls a hosted API or runs its own AI model — it's a local, offline analysis tool.

Full docs: github.com/Vovy-AI/vovy-cli

License

MIT