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

liquidpad-mcp

v0.2.0

Published

Model Context Protocol server for LiquidPad — verify, deploy, and inspect tokens launched on Base from Claude / Cursor / any MCP client.

Readme

liquidpad-mcp

Model Context Protocol server for LiquidPad — the autonomous token launcher on Base.

Add LiquidPad tools to Claude Desktop, Cursor, Continue, or any MCP-compatible client. Verify tokens, check stats, inspect burn cycles, and deploy tokens — all from your AI assistant.

Quick start

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%/Claude/claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "liquidpad": {
      "command": "npx",
      "args": ["-y", "liquidpad-mcp"],
      "env": {
        "LIQUIDPAD_API_KEY": "your-api-key-here"
      }
    }
  }
}

Cursor

Add to .cursor/mcp.json in your project:

{
  "mcpServers": {
    "liquidpad": {
      "command": "npx",
      "args": ["-y", "liquidpad-mcp"],
      "env": {
        "LIQUIDPAD_API_KEY": "your-api-key-here"
      }
    }
  }
}

Kiro

Add to .kiro/settings/mcp.json:

{
  "mcpServers": {
    "liquidpad": {
      "command": "npx",
      "args": ["-y", "liquidpad-mcp"],
      "env": {
        "LIQUIDPAD_API_KEY": "your-api-key-here"
      }
    }
  }
}

Get an API key

  1. Open @liquidpadbot on Telegram
  2. /start/setaddress 0xYOUR_WALLET/apikey
  3. Set LIQUIDPAD_API_KEY in your env

API key is only required for deploy and list-my-tokens tools. Public tools (verify, stats, burn proof) work without auth.

Examples

Ready-to-paste client configs and a standalone smoke test live in examples/:

  • claude-desktop.json, cursor.json, kiro.json, cline.json — copy the liquidpad block into your client's MCP config
  • smoke.mjs — launches the server over stdio, lists tools, calls a read-only tool. No API key needed:
node examples/smoke.mjs

Tools

| Tool | Auth | Description | |------|------|-------------| | verify_token | — | Confirm a token was launched through LiquidPad | | get_stats | — | Protocol-level stats (tokens, volume, momentum) | | get_burn_proof | — | All burn + buyback cycles with tx hashes | | get_token_stats | — | Live USD data for all LiquidPad tokens | | get_treasury | — | Auto-claim + auto-buyback pipeline status | | get_token_page | — | Canonical URLs (page, embed, OG, verify API) | | list_my_tokens | 🔑 | Tokens you deployed | | agent_status | 🔑 | Your agent's current state | | deploy_token | 🔑 | Deploy with explicit name + symbol | | deploy_from_concept | 🔑 | AI-generate concept + deploy | | chat | 🔑 | OpenAI-compatible chat completion via LiquidPad LLM Gateway | | list_gateway_models | 🔑 | Models available to your $LPAD tier | | get_gateway_usage | 🔑 | Quota + rate-limit state, key status |

13 tools total. Read tools (no 🔑) work anonymously; the rest need an API key from @liquidpadbot.

Environment variables

| Var | Default | Description | |-----|---------|-------------| | LIQUIDPAD_API_KEY | — | Your personal API key (from @liquidpadbot) | | LIQUIDPAD_SITE | https://www.liquidpad.site | Website base URL | | LIQUIDPAD_API_BASE | https://api.liquidpad.site | Backend API URL | | LIQUIDPAD_GATEWAY | same as LIQUIDPAD_API_BASE | LLM Gateway base URL (rarely changed) |

Fee structure

Every token deployed through LiquidPad:

  • 80% trading fees → deployer wallet
  • 15% → $LPAD buyback & burn (permanent supply reduction)
  • 5% → $LIQ buyback (Liquid Protocol ecosystem support)

What's new in v0.2

LLM Gateway access via three tools — chat, list_gateway_models, get_gateway_usage. Your LIQUIDPAD_API_KEY now covers both deploy AND inference under one credential.

> Show me which gateway models I can call
[agent → list_gateway_models]
liquidpad-trial    tier 0   trial only
liquidpad-base     tier 1+
liquidpad-fast     tier 2+
liquidpad-large    tier 3+
> Use liquidpad-trial to draft a token name about late-night ramen
[agent → chat: model=liquidpad-trial, messages=[...]]
"Slurpcoin" or "MIDNIGHTBROTH" — pick a vibe and i'll narrate further.

Quotas and per-minute rate limits scale with your $LPAD tier. Track usage anytime with get_gateway_usage.

Links

  • Website: https://www.liquidpad.site
  • Docs: https://www.liquidpad.site/docs
  • MCP Guide: https://www.liquidpad.site/mcp
  • Telegram: https://t.me/liquidpadbot
  • ERC-8004 Agent #50962: https://8004agents.ai/base/agent/50962

License

MIT