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

@tankpkg/mcp-server

v0.9.1

Published

MCP server for Tank - scan and publish AI agent skills from your editor

Readme

@tankpkg/mcp-server

MCP (Model Context Protocol) server for Tank — manage AI agent skills directly from your editor. Full CLI parity: every tank command is available as an MCP tool.

Features

Authentication

  • login — Authenticate with Tank via GitHub OAuth
  • logout — Clear stored credentials
  • whoami — Show current user info

Project Setup

  • init-skill — Create skills.json and SKILL.md scaffold

Publishing & Discovery

  • publish-skill — Publish a skill to the Tank registry (with dry-run support)
  • search-skills — Search the Tank registry for skills
  • skill-info — Get detailed information about a specific skill

Installation & Management

  • install-skill — Install a skill with SHA-512 verification
  • update-skill — Update skills within semver range
  • remove-skill — Remove a skill and clean up lockfile

Security & Verification

  • scan-skill — Scan any directory for security issues (skills.json not required)
  • verify-skills — Verify lockfile integrity
  • audit-skill — Show security scan results and verdict
  • skill-permissions — Display per-skill permission summary

Agent Integration

  • link-skill — Symlink a skill into an agent workspace
  • unlink-skill — Remove a skill symlink

Diagnostics

  • doctor — Check config, auth, registry connectivity, and Node.js version

Installation

Claude Code

Add to .claude/settings.json or your project's .mcp.json:

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

Cursor

Add to ~/.cursor/mcp.json:

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

VS Code (Copilot)

Add to .vscode/mcp.json:

{
  "servers": {
    "tank": {
      "command": "npx",
      "args": ["-y", "@tankpkg/mcp-server"]
    }
  }
}

Authentication

The MCP server shares authentication with the Tank CLI. If you've already run tank login, you're authenticated!

Alternatively, set the TANK_TOKEN environment variable:

{
  "mcpServers": {
    "tank": {
      "command": "npx",
      "args": ["-y", "@tankpkg/mcp-server"],
      "env": {
        "TANK_TOKEN": "tank_your_token_here"
      }
    }
  }
}

Usage Examples

Once configured, talk to your AI agent naturally:

"Initialize a new skill in this directory"
"Scan my skill for security issues"
"Publish my skill to Tank"
"Install @acme/code-review"
"Update all my skills"
"Search Tank for testing skills"
"Show permissions for my installed skills"
"Run tank doctor to check my setup"
"Audit @acme/code-review for security issues"
"Link this skill to my Claude workspace"

Development

# Install dependencies
bun install

# Build
bun build

# Run tests
bun test

# Start the server (stdio mode)
bun start

License

MIT