@rog0x/mcp-web-tools

@rog0x

About @rog0x/mcp-web-tools

MCP server for AI agents: web content extraction, DuckDuckGo search, site monitoring, HTML to markdown. No API keys needed. Install: npx @rog0x/mcp-web-tools

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "web-tools": {
      "command": "npx",
      "args": [
        "@rog0x/mcp-web-tools"
      ]
    }
  }
}

Tools

Extract structured content from a URL: title, headings, paragraphs, links, images, and metadata

Search the web using DuckDuckGo and return structured results with titles, URLs, and snippets

Check if a website is up, measure response time, and get HTTP details

Convert HTML content or a URL to clean, readable markdown. Removes scripts, styles, and navigation.

Extract content from multiple URLs in parallel. Returns results for each URL.

Overview

What is @rog0x/mcp-web-tools?

A Model Context Protocol server that provides AI agents with web capabilities: content extraction, web search via DuckDuckGo, site monitoring, and HTML‑to‑markdown conversion, all through a clean tool interface.

How to use @rog0x/mcp-web-tools?

Install by adding a mcpServers entry to your Claude Code or Claude Desktop config using npx @rog0x/mcp-web-tools, or globally via npm install -g @rog0x/mcp-web-tools and run mcp-web-tools. Invoke the five exposed tools: web_extract, web_search, web_monitor, html_to_markdown, and web_multi_extract.

Key features of @rog0x/mcp-web-tools

No API keys required — uses DuckDuckGo for search.
Fast parallel extraction with 15‑second request timeout.
Clean output — strips scripts, styles, and ads.
Lightweight — minimal dependencies, no headless browser.
Production‑ready error handling and input validation.

Use cases of @rog0x/mcp-web-tools

Extract structured content (titles, headings, links) from any URL.
Search the web using DuckDuckGo without an API key.
Monitor website uptime, response time, and HTTP headers.
Convert any URL or HTML into clean Markdown.
Batch extract content from multiple URLs in parallel.

FAQ from @rog0x/mcp-web-tools

What runtime does @rog0x/mcp-web-tools require?

Node.js 18 or newer.

Do I need an API key for web search or content extraction?

No — web search uses DuckDuckGo and all other tools work over direct HTTP without any API keys.

How does the server handle timeouts and errors?

Each request has a 15‑second timeout, and the server includes proper error handling and input validation.

Is a headless browser needed to extract content?

No — the server is lightweight and works without a headless browser, using direct HTTP requests.

Under what license is @rog0x/mcp-web-tools distributed?

MIT — rog0x.

Frequently asked questions

What runtime does @rog0x/mcp-web-tools require?

Node.js 18 or newer.

Do I need an API key for web search or content extraction?

No — web search uses DuckDuckGo and all other tools work over direct HTTP without any API keys.

How does the server handle timeouts and errors?

Each request has a 15‑second timeout, and the server includes proper error handling and input validation.

Is a headless browser needed to extract content?

No — the server is lightweight and works without a headless browser, using direct HTTP requests.

Under what license is @rog0x/mcp-web-tools distributed?

MIT — rog0x.

Comments

Basic information

More Search MCP servers

Baidu AI Search

baidubce

appbuilder-sdk, 千帆AppBuilder-SDK帮助开发者灵活、快速的搭建AI原生应用

583

Search Console Mcp

saurabhsharma2u

Search & analytics data as infrastructure — MCP server for Google Search Console, Bing Webmaster Tools, and GA4, designed for AI agents and automation.

205