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

@letsping/mcp

v0.3.1

Published

LetsPing Behavioral Shield MCP Server for Claude and Cursor

Readme

@letsping/mcp

The official Model Context Protocol (MCP) server for LetsPing.

This package enables any MCP-compliant agent (Claude Desktop, Cursor, LangChain, etc.) to natively invoke the Behavioral Shield, parking the context and "Asking a Human" for approval or help before deploying destructive API changes on your machine.

Usage

Zero-Config (via npx)

You can run the server directly without installing it, as long as you have your API Key.

Claude Desktop Config (claude_desktop_config.json):

{
  "mcpServers": {
    "letsping": {
      "command": "npx",
      "args": ["-y", "@letsping/mcp"],
      "env": {
        "LETSPING_API_KEY": "lp_sk_..."
      }
    }
  }
}

Tools Provided

ask_human

Request approval or input from a human operator.

Arguments:

  • service (string): The name of your agent (e.g. "billing-bot").
  • action (string): What you are trying to do (e.g. "refund-user").
  • payload (object): The data needing review (e.g. { "amount": 50, "user_id": "123" }).
  • priority (string, optional): "low" | "medium" | "high" | "critical". Defaults to "medium".
  • role (string, optional): Who should approve this? (e.g. "finance", "devops").
  • timeout (number, optional): Max wait time in milliseconds (default ~24h).

Return shape (content text JSON):

// APPROVED, no modifications
{
  "status": "APPROVED",
  "executed_payload": { /* final payload */ }
}

// APPROVED, with human modifications
{
  "status": "APPROVED_WITH_MODIFICATIONS",
  "message": "The human reviewer authorized this action but modified your original payload. Please review the diff_summary to learn from this correction.",
  "diff_summary": { "changes": { /* field-level diff */ } },
  "original_payload": { /* as requested by the agent */ },
  "executed_payload": { /* what will actually run */ }
}

// REJECTED
{
  "status": "REJECTED",
  "message": "The human operator rejected this action. Do not proceed with the plan.",
  "metadata": { /* optional audit fields */ }
}

How an MCP agent should behave:

  • Never proceed with the risky action if status === "REJECTED".
  • If status === "APPROVED_WITH_MODIFICATIONS", prefer executed_payload over the original; optionally learn from diff_summary.
  • If status === "APPROVED", proceed using executed_payload.

Development

  1. Clone the repo.
  2. Run pnpm install.
  3. Run pnpm build.