Web Content Extractor (agent Optimized)
@agenson-tools
About Web Content Extractor (agent Optimized)
Agent-optimized MCP server for extracting clean, structured content from web pages
Basic information
Category
AI & Agents
License
MIT
Runtime
node
Transports
stdio
Publisher
agenson-tools
Submitted by
agenson-horrowitz
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"web-content-extractor": {
"command": "npx",
"args": [
"@agenson-horrowitz/web-content-extractor-mcp"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Web Content Extractor (agent Optimized)?
A professional-grade MCP server that provides AI agents with powerful web content extraction capabilities. It extracts clean, structured, LLM-optimized content from web pages, saving tokens and improving agent accuracy by converting raw HTML into markdown, JSON, or structured data.
How to use Web Content Extractor (agent Optimized)?
Install via npm globally (npm install -g @agenson-horrowitz/web-content-extractor-mcp) or configure it in Claude Desktop or Cline by adding the server to the respective MCP config JSON with command npx and args ["@agenson-horrowitz/web-content-extractor-mcp"]. Once configured, users invoke specific tools such as extract_article, extract_structured_data, extract_links, screenshot_to_markdown, or batch_extract.
Key features of Web Content Extractor (agent Optimized)
- Advanced article extraction with clean markdown and metadata
- Structured data parsing (tables, lists, forms) as JSON
- Intelligent link analysis with categorization and context
- Visual layout analysis via screenshot-to-markdown
- High-performance batch processing with rate limiting
- Sub-2-second response times and token-efficient output
Use cases of Web Content Extractor (agent Optimized)
- AI agent reads and summarizes news articles, blog posts, or research papers
- Extract pricing tables and feature comparisons for competitive analysis
- Perform bulk content audits across multiple competitor websites
- Analyze UI layouts and visual content for design understanding
- Discover and categorize internal/external links for site mapping or SEO
FAQ from Web Content Extractor (agent Optimized)
How does Web Content Extractor (agent Optimized) differ from raw HTML scraping?
It extracts LLM-optimized content with structured metadata, saving tokens and improving accuracy compared to raw HTML. Uses Mozilla Readability, Playwright, and other libraries for clean output.
What are the runtime requirements and dependencies?
Requires Node.js; uses Playwright for browser automation, Mozilla Readability for content extraction, Metascraper for metadata, Turndown for HTML-to-markdown, and JSDOM for DOM manipulation.
Where does the extracted data live?
All data is extracted from provided URLs and returned in the tool response; no persistent storage on the server side is mentioned.
What are the known limits of Web Content Extractor (agent Optimized)?
Average response time < 2 seconds; rate limit of 10 extractions/second (configurable); content limit of 50MB per extraction; free tier allows 500 extractions/month, with higher limits on paid plans.
What transport and authentication options are available?
Uses MCP protocol via stdio transport (default setup via npx). Authentication is not required for local usage; for hosted usage via MCPize or direct API, it supports API keys and crypto micropayments (USDC on Base chain).
More AI & Agents MCP servers
MCP-LLM Bridge
patruffBridge between Ollama and MCP servers, enabling local LLMs to use Model Context Protocol tools
MCP Claude Code
SDGLBLMCP implementation of Claude Code capabilities and more
Shell and Coding agent for Claude and other mcp clients
rusiaamanShell and coding agent on mcp clients
Perplexity MCP Server
DaInfernalCoderA Model Context Protocol (MCP) server for research and documentation assistance using Perplexity AI. Won 1st @ Cline Hackathon
Mcp Agent
lastmile-aiBuild effective agents using Model Context Protocol and simple workflow patterns
Comments