# Web Scraper

> Use this tool when you need to extract content from web pages, especially those with heavy JavaScript usage or single-page applications. It solves problems of unreliable web scraping and limited access to dynamic site content, providing article-focused extraction with HTML tag stripping for efficient LLM processing. With interfaces for both MCP server and direct LangChainGo tool integration, it serves developers, teams, and applications requiring robust web content extraction for AI workflows and conversational interfaces.

Canonical page: https://skillsregistry.net/skills/lmorg-web-scraper  
JSON: https://api.skillsregistry.net/v1/skills/lmorg-web-scraper

## Description

This MCP server provides AI assistants with web scraping capabilities using Google Chrome's headless APIs to extract content from web pages, with automatic fallback to Go's HTTP client when Chrome is unavailable. Built by Laurence Morgan using Go with chromedp integration, it handles JavaScript-heavy sites and single-page applications by rendering pages in a real browser environment, preferentially extracting article content over full page body, and includes HTML tag stripping to reduce token count for LLM processing. Serves developers needing reliable web content extraction for AI workflows, teams requiring JavaScript-capable scraping for dynamic sites, and applications that need to process web content through conversational interfaces with both MCP server and direct LangChainGo tool integration options.

## Trust

- **Trust score (0–1):** 0.99
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** browser-automation
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/lmorg-web-scraper)
- **Repository:** <https://github.com/lmorg/mcp-web-scraper>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "lmorg-web-scraper"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/lmorg-web-scraper` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/lmorg-web-scraper/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt
