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

agentvault-tools

v0.3.1

Published

The essential MCP toolkit — web search, fetch, memory, calculator, and more. Zero API keys. One install.

Readme

🏴‍☠️ agentvault-tools

npm version License: MIT

The essential MCP toolkit — 9 tools, zero API keys, one install.

Give your AI agent web search, page fetching, persistent memory, timezone conversion, and a calculator — all in a single MCP server. No API keys, no accounts, no cloud required.

Why this?

Starting with MCP? You need this one package:

npx agentvault-tools

That's it. Your agent now has 9 tools.

Tools

🔍 Web

| Tool | Description | |------|-------------| | web_search | Search via DuckDuckGo (no API key!) | | web_fetch | Fetch any URL → clean text |

🧮 Utility

| Tool | Description | |------|-------------| | datetime | Current time in any timezone | | calc | Evaluate math expressions |

🧠 Memory (persistent, local)

| Tool | Description | |------|-------------| | save_memory | Save text with tags & importance | | search_memory | Full-text search across all memories | | list_memories | Browse recent or filter by tag | | delete_memory | Remove a memory | | memory_stats | Usage statistics |

Memory persists across sessions in a local SQLite database (~/.agentvault/memory.db). Data never leaves your machine.

Quick Start

Claude Desktop

{
  "mcpServers": {
    "tools": {
      "command": "npx",
      "args": ["-y", "agentvault-tools"]
    }
  }
}

Cursor / Windsurf

{
  "tools": {
    "command": "npx",
    "args": ["-y", "agentvault-tools"]
  }
}

What happens next

Your agent can now:

  • Search: "Find the latest Node.js release notes" → web_search
  • Read: "What does that page say?" → web_fetch
  • Remember: "Remember that the API key is xyz" → save_memory
  • Recall: "What was that API key?" → search_memory
  • Calculate: "What's 15% of 2,450?" → calc
  • Time: "What time is it in Tokyo?" → datetime

Privacy

  • All data stays local. Memory is stored at ~/.agentvault/memory.db
  • No telemetry by default. Set AGENTVAULT_TELEMETRY=true to opt in
  • Search queries and URLs are never sent even with telemetry on

Part of AgentVault

🏴‍☠️ AgentVault — The essential toolkit for AI agents.

| Package | What it does | |---------|-------------| | agentvault-tools | 🛠️ 9-tool MCP starter kit (you are here) | | agentvault-memory | 🧠 Local-first persistent memory (standalone) | | agentvault-guard | 🛡️ Tool poisoning detection | | agentvault-gateway | 🔌 MCP proxy with audit logging | | agentvault-score | 📊 Quality scoring (A+ to F) | | agentvault-retry | 🔄 Resilient calls with backoff | | agentvault-cache | ⚡ Smart result caching |

MIT License