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

@sthbryan/web-search-mcp

v0.2.2

Published

Lightweight MCP server for web search and scraping

Readme

Web Search MCP Server

A Model Context Protocol server for web search and scraping using DuckDuckGo

Overview

This MCP server provides tools for AI agents to search the web, fetch page content, and query specific elements from pages. It uses DuckDuckGo as the primary search engine with a hybrid approach:

  • API search for fast, direct results
  • HTML scraping as fallback when API is unavailable
  • Native fetch for page retrieval and element queries

No headless browser or complex dependencies required.

Tools

search — Search DuckDuckGo

{ "query": "rust programming", "limit": 5 }

Response:

{
  "query": "rust programming language",
  "source": "api",
  "results": [
    { "title": "The Rust Programming Language", "url": "https://rust-lang.org" }
  ]
}

fetch_page — Get page content (HTML/markdown/text)

{ "url": "https://example.com", "type": "markdown" }

Response:

{
  "url": "https://example.com",
  "type": "markdown",
  "source": "native",
  "length": 1234,
  "content": "# Example\n\nContent here..."
}

query — Extract elements via CSS selector + text filter

{
    "url": "https://example.com",
    "selector": "h1, h2",
    "text": "intro"
}

Response:

{
  "url": "https://example.com",
  "source": "native",
  "selector": "h1, h2",
  "text": "intro",
  "result": ["Introduction", "Getting Started"]
}

Requirements

  • Node.js 18+ or Bun
  • Internet connection (for DuckDuckGo API/scraping)

Installation

# Clone and install dependencies
bun install

# Build for production
bun run build

Add to your MCP servers config:

{
  "mcpServers": {
    "web-search": {
      "command": "bunx",
      "args": ["-y", "@sthbryan/web-search-mcp"]
    }
  }
}

For client-specific configuration, see INSTALL.md.

Architecture

┌─────────────────────────────────────────────────────────────┐
│                        MCP Client                           │
│                       Coding Agent                          │
└─────────────────────────┬───────────────────────────────────┘
                          │ JSON-RPC
                          ▼
┌─────────────────────────────────────────────────────────────┐
│                   Web Search MCP Server                     │
│        ┌─────────┐   ┌─────────┐   ┌─────────┐              │
│        │  search │   │  fetch  │   │  query  │  ← Tools     │
│        └───┬─────┘   └───┬─────┘   └───┬─────┘              │
│            │             │             │                    │
│            ▼             ▼             ▼                    │
│  ┌─────────────────────────────────────────────────────────┐│
│  │                    searchHandler()                      ││
│  │              (parallel API + scraping)                  ││
│  └──────────────────────────┬──────────────────────────────┘│
│                             │                               │
│                ┌────────────┴────────────┐                  │
│                ▼                         ▼                  │
│         ┌────────────┐           ┌────────────┐             │
│         │ DuckDuckGo │           │   Native   │             │
│         │    API     │           │   fetch    │             │
│         └────────────┘           └────────────┘             │
└─────────────────────────────────────────────────────────────┘

How Search Works

User Query: "MCP protocol"
     │
     ├─► DuckDuckGo API ──► Fast results
     │                         │
     └─► DuckDuckGo Lite ──► HTML scraping
         (on fallback)          │
                                ▼
                         ┌────────────┐
                         │   Merge    │
                         │ + Dedupe   │
                         └────────────┘
                                │
                                ▼
                         Final Results

Development

# Run in development mode
bun run dev

# Build for production
bun run build

# Type check
bun run check

License

MIT