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

@quantustik/mcp-server

v1.0.2

Published

Quantustik: quantum-model S&P 500 analytics for AI agents — risk-first BUY/WAIT/AVOID/EXIT signals with trade plans, calibrated multi-horizon forecasts, whole-universe scans and market conditions. Educational research, not investment advice. This package

Readme

Quantustik MCP server — quantum-model S&P 500 analytics

Quantustik is a stock-analytics platform that forecasts S&P 500 price paths with a quantum-mechanics model (the Schrödinger equation and Feynman path integrals), layers a machine-learning classifier and a market-conditions read on top, and turns the result into risk-first BUY / WAIT / AVOID / EXIT signals — each with entry price, stop-loss, take-profit ladder and position sizing, plus calibrated 90% confidence bands and a live, auditable track record that includes the losses.

What the analysis gives you, per ticker and for the whole index:

  • a signal with the full trade plan behind it (only actionable at ≥2:1 reward-to-risk), and a two-sided explanation of why the model made the call;
  • multi-horizon price forecasts (1mo / 3mo / 6mo / 1y) with measured, published calibration — never a bare point estimate;
  • whole-universe scans (conviction / direction / sector filters), a risk-vetted shortlist of asymmetric setups, market conditions and an overheating gauge, backtests, fundamentals, dividends and more — 24 tools in total.

Who it is for: AI agents and their users doing market research — analysts, self-directed investors, and anyone who wants honest, uncertainty-explicit market context inside Claude, Cursor, ChatGPT or any other MCP client. Bullish calls are deliberately rare and earned: the model prefers saying WAIT to flattering you.

Educational research only — not investment advice. Nothing here is a recommendation to buy or sell any security. Calibration is measured, not guaranteed; past model performance does not predict future results.

What this package is

A thin stdio proxy to Quantustik's hosted MCP server. It lets MCP clients that only support local stdio servers (Claude Desktop, Cursor, Windsurf, and others) reach the live, keyless, streamable-HTTP endpoint at https://quantustik.com/mcp.

This package does not implement an MCP server itself, run any model locally, or cache any data. It is a small wrapper around mcp-remote pointed at our hosted endpoint. Every tool call is forwarded live to quantustik.com and answered from the same data and quota system as the hosted endpoint.

If your MCP client supports remote streamable-HTTP servers directly, you don't need this package at all — just point it at https://quantustik.com/mcp. This wrapper exists only for stdio-only clients.

The full tool catalog lives at quantustik.com/developers.

Usage

Claude Desktop / Cursor / Windsurf

Add to your MCP client config (e.g. claude_desktop_config.json):

{
  "mcpServers": {
    "quantustik": {
      "command": "npx",
      "args": ["-y", "@quantustik/mcp-server"]
    }
  }
}

Command line

npx -y @quantustik/mcp-server

This starts a local stdio MCP server that proxies to https://quantustik.com/mcp. Anonymous use is allowed under a per-IP hourly quota; no setup required.

Optional: raise your quota with an API key

Get a free key at quantustik.com/developers, then set it as an environment variable:

{
  "mcpServers": {
    "quantustik": {
      "command": "npx",
      "args": ["-y", "@quantustik/mcp-server"],
      "env": {
        "QUANTUSTIK_API_KEY": "your-key-here"
      }
    }
  }
}

Environment variables

| Variable | Purpose | Default | |---|---|---| | QUANTUSTIK_API_KEY | Sent as Authorization: Bearer <key> to raise the anonymous per-IP hourly quota. | none (anonymous) | | QUANTUSTIK_MCP_URL | Override the remote endpoint (mainly for local development against a non-production instance). | https://quantustik.com/mcp |

Any additional CLI arguments you pass are forwarded to the underlying mcp-remote proxy (e.g. --debug).

How it works

npx @quantustik/mcp-server runs a small Node script (bin/quantustik-mcp.js) that spawns mcp-remote against https://quantustik.com/mcp using the http-only transport (our endpoint is streamable-HTTP, not SSE). mcp-remote speaks stdio to your MCP client on one side and streamable-HTTP to our server on the other — this package just pins the URL, transport, and optional auth header so you don't have to remember them.

Source

Server implementation (Python, FastMCP): the hosted endpoint's source lives in mcplafed/autoevolve (app/mcp_server.py, server.json). This wrapper repo only contains the thin npm client shown above.

Disclaimer

All signals, forecasts, and market data returned by the Quantustik MCP server are for educational and research purposes only and do not constitute personalized financial advice. Past model performance does not guarantee future results. Always consult a qualified financial professional before making investment decisions.

License

MIT — see LICENSE.