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

@thunderbit/mcp-server

v1.0.4

Published

Thunderbit MCP Server — AI-powered web scraping and structured data extraction for Claude, ChatGPT, and other MCP-compatible AI assistants.

Readme

@thunderbit/mcp-server

Thunderbit MCP Server — AI-powered web scraping and structured data extraction for Claude, ChatGPT, and any MCP-compatible AI assistant.

npm version MCP Compatible

A Model Context Protocol (MCP) server that lets AI assistants:

  • Convert any web page into clean, LLM-ready Markdown
  • Extract structured data from web pages using JSON Schema
  • Get AI-suggested fields for unknown page structures
  • Run batch jobs on up to 100 URLs at a time

Backed by the Thunderbit Open API. Get a free API key at app.thunderbit.com/console/api-keys.


Quick Start (Claude Desktop)

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

{
  "mcpServers": {
    "thunderbit": {
      "command": "npx",
      "args": ["-y", "@thunderbit/mcp-server"],
      "env": {
        "THUNDERBIT_API_KEY": "tb_your_api_key_here"
      }
    }
  }
}

Restart Claude Desktop. The Thunderbit tools should appear in the tool picker.

Quick Start (Cursor / Cline / other MCP clients)

Same config shape — command: "npx", args: ["-y", "@thunderbit/mcp-server"].

Manual install

npm install -g @thunderbit/mcp-server
thunderbit-mcp

Or one-shot:

THUNDERBIT_API_KEY=tb_xxx npx -y @thunderbit/mcp-server

Tools

| Tool | Cost | Purpose | |------|------|---------| | thunderbit_suggest_fields | Free | Discover what data is on a page | | thunderbit_distill | 1 credit | Page → clean Markdown | | thunderbit_extract | 20 credits | Page → structured JSON via schema | | thunderbit_batch_distill_create | 1 credit/URL | Distill up to 100 URLs | | thunderbit_batch_distill_status | Free | Poll batch distill results | | thunderbit_batch_extract_create | 20 credits/URL | Extract from up to 100 URLs | | thunderbit_batch_extract_status | Free | Poll batch extract results |

Recommended workflow

1. thunderbit_suggest_fields  →  See what data the page has
2. thunderbit_extract         →  Pull it as structured JSON
   OR thunderbit_distill      →  Get the page as Markdown
3. (Bulk) batch_*_create      →  Submit up to 100 URLs
4. (Bulk) batch_*_status      →  Poll until done

Configuration

| Env Var | Description | Default | |---------|-------------|---------| | THUNDERBIT_API_KEY | API key (tb_...) | — (required) | | THUNDERBIT_API_BASE_URL | API base URL | https://openapi.thunderbit.com | | THUNDERBIT_TIMEOUT_MS | HTTP timeout per call | 120000 |

API key precedence: tool-call apiKey argument → THUNDERBIT_API_KEY env var → error.


Errors

| HTTP Status | Hint | |-------------|------| | 401 | Invalid API key — check THUNDERBIT_API_KEY | | 402 | Out of credits — top up at app.thunderbit.com/console/billing | | 429 | Rate-limit exceeded — retry later |

Errors are returned as MCP tool errors (isError: true) so the AI can react gracefully.


Local Development

git clone https://github.com/thunderbit-com/thunderbit-mcp-server.git
cd thunderbit-mcp-server/packages/mcp-server
npm install
THUNDERBIT_API_KEY=tb_xxx node bin/cli.js

The server speaks MCP over stdio. To test interactively, use @modelcontextprotocol/inspector:

npx @modelcontextprotocol/inspector node bin/cli.js

License

MIT © Thunderbit