io.github.rog0x/web (MCP Server)

A MCP (Model Context Protocol) server offering web extraction, search, monitoring, and HTML-to-markdown conversion for AI agents. It exposes tools to retrieve structured content from URLs, perform web searches, monitor site health, and render HTML as Markdown, enabling richer model context.

🛠️ Key Features

Web content extraction: title, headings, paragraphs, links, images, metadata
Web search via DuckDuckGo (no API key)
Site monitoring: uptime checks, response times, HTTP headers
HTML/URL to Markdown conversion
TypeScript-based implementation and MCP compatibility

🚀 Use Cases

Equip AI agents with live web context for research or decision making
Pull structured data from web pages for summarization
Monitor critical sites and track performance
Convert web content into Markdown for model-friendly prompts

⚡ Developer Benefits

Clear MCP server interface tailored for AI agents
Reusable tools: web_extract, web_search, web_monitor, html_to_markdown
Lightweight, typed TypeScript tools suitable for integration

⚠️ Limitations

Web search uses DuckDuckGo without API keys; results may vary
HTML-to-markdown fidelity depends on source HTML quality
Real-time monitoring depends on external network conditions

MCP Web Tools

A powerful MCP (Model Context Protocol) server that gives AI agents web superpowers. Extract content, search the web, monitor sites, and convert HTML to markdown — all through a clean tool interface.

Tools

Tool	Description
`web_extract`	Extract structured content from any URL (title, headings, paragraphs, links, images, metadata)
`web_search`	Search the web via DuckDuckGo — no API key needed
`web_monitor`	Check if a site is up, measure response time, get HTTP headers
`html_to_markdown`	Convert any URL or HTML to clean markdown
`web_multi_extract`	Extract content from multiple URLs in parallel

Installation

For Claude Code

Add to your Claude Code MCP settings (~/.claude/settings.json):

json

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

For Claude Desktop

Add to claude_desktop_config.json:

json

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

Manual Installation

bash

npm install -g @rog0x/mcp-web-tools
mcp-web-tools

Usage Examples

Extract content from a webpage

code

Use web_extract to get the main content from https://example.com

Search the web

code

Use web_search to find "best TypeScript frameworks 2026"

Monitor a website

code

Use web_monitor to check if https://api.example.com is responding

Convert page to markdown

code

Use html_to_markdown to convert https://docs.example.com/guide to readable markdown

Batch extraction

code

Use web_multi_extract to get content from these URLs: [url1, url2, url3]

Features

No API keys required — uses DuckDuckGo for search, direct HTTP for everything else
Fast — parallel extraction, 15s timeout per request
Clean output — strips scripts, styles, ads; extracts meaningful content
Lightweight — minimal dependencies, no headless browser needed
Production-ready — proper error handling, timeouts, input validation

Requirements

Node.js 18+

License

MIT — rog0x

io.github.rog0x/web

io.github.rog0x/web (MCP Server)

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

Topics

MCP Web Tools

Tools

Installation

For Claude Code

For Claude Desktop

Manual Installation

Usage Examples

Extract content from a webpage

Search the web

Monitor a website

Convert page to markdown

Batch extraction

Features

Requirements

License

Install

Related servers