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

@hopperd-sdk/core

v0.1.4

Published

Observability for MCP servers

Readme

@hopperd-sdk/core

Analytics and instrumentation for MCP servers with automatic user intent capture.

Installation

npm install @hopperd-sdk/core

Quick Start (Recommended)

One line of code to track all your tools with automatic user intent capture:

import { McpServer } from '@modelcontextprotocol/sdk/server/mcp.js'
import { track } from '@hopperd-sdk/core'
import { z } from 'zod'

// Create your MCP server
const server = new McpServer({
  name: 'my-server',
  version: '1.0.0',
})

track(server, {
  apiKey: process.env.HOPPERD_API_KEY,
  serverName: 'my-server',
})

server.tool(
  'get-weather',
  'Get weather forecast',
  {
    location: z.string().describe('Location to get weather for'),
  },
  async ({ location }) => {
    // Your tool logic here
    const weather = await getWeatherData(location)
    return {
      content: [
        {
          type: 'text',
          text: `Weather in ${location}: ${weather}`,
        },
      ],
    }
  },
)

// All tools are now automatically tracked!

How It Works

The track() function automatically:

  1. Enhances tool schemas with a _context parameter
  2. Captures user intent - AI explains why the tool was called
  3. Tracks everything - params, results, errors, duration
  4. Keeps tools clean - handlers receive params without _context

When an AI assistant calls your tool, it automatically provides context:

{
  "location": "New York",
  "_context": "User wants to check weather conditions before planning outdoor activities"
}

This context is captured as "user intent" in your analytics!

Configuration

track(server, {
  apiKey: 'hopp_your_api_key',
  serverName: 'my-mcp-server',
})

Required:

  • apiKey - Your Hopperd API key
  • serverName - Name to identify this server in analytics

What Gets Tracked

Every tool call captures:

  • Tool name and server name
  • Full parameters (JSON)
  • User intent - AI's explanation of why the tool was called
  • Results - Complete tool output (JSON)
  • Errors - Full error messages and stack traces
  • Duration - Execution time in milliseconds
  • Timestamps - When tools are invoked

All tracking is done asynchronously and will not impact your MCP server performance.

Key Benefits

  • One-line setup - No manual tool wrapping
  • Automatic user intent - Understand why users call your tools
  • Full debugging data - Complete params, results, and errors
  • Zero tool changes - Tools work exactly as before
  • Transparent operation - Handlers receive clean parameters