Web Content Extractor
This server wraps Mozilla Readability and Puppeteer to turn messy web pages into clean markdown and JSON that won't burn your context window. You get five tools: extract_article for blog posts and docs, extract_structured_data for tables and forms, extract_links with smart categorization (internal, external, social, downloads), screenshot_to_markdown for visual layout analysis, and batch_extract for processing multiple URLs with rate limiting. All responses include timing metrics and token counts. The article extractor can handle JavaScript-heavy SPAs and lets you cap output length. Runs via stdio transport, installs through npx, and processes most pages in under two seconds. Built for agents that need to read the web without choking on raw HTML.
- tools
- 5
- transport
- STDIO
- last updated
- Apr 2, 2026
Tools
5 toolsPublic tool metadata for what this MCP can expose to an agent.
extract_articleExtract clean article content as agent-optimized markdown.
Extract clean article content as agent-optimized markdown.
No parameter schema in public metadata yet.
extract_structured_dataExtract structured data (tables, lists, forms) as JSON.
Extract structured data (tables, lists, forms) as JSON.
No parameter schema in public metadata yet.
extract_linksGet all links with intelligent categorization and context.
Get all links with intelligent categorization and context.
No parameter schema in public metadata yet.
screenshot_to_markdownVisual layout analysis via screenshot conversion.
Visual layout analysis via screenshot conversion.
No parameter schema in public metadata yet.
batch_extractProcess multiple URLs in parallel with error recovery.
Process multiple URLs in parallel with error recovery.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
Web Content Extractor MCP Server (Agent-Optimized)
A professional-grade MCP server that provides AI agents with powerful web content extraction capabilities. Built specifically for the agent economy by Agenson Horrowitz.
🤖 Why This Exists
Details
- Repository
- github.com/agenson-tools/web-content-extractor-mcp
- Category
- Search & Web Crawling
- Package
@agenson-horrowitz/web-content-extractor-mcp- Transport
- STDIO
- Registry
- MCP registry, active
More from agenson-tools
Related Search & Web Crawling MCP servers
View all
AgentIndexagentndx/agentndxSearch 15K+ MCP services, A2A agents, and x402 APIs from 5 registries. Paid via x402 (USDC on Base).0stars
Avalanche AVAX MCPairpote/avalanche-mcp-vscodeSearch and retrieve Avalanche blockchain documentation for building on AVAX.0stars
Kylas CRMakshaykylas94/mcpMCP server for Kylas CRM: create, search, and manage leads. Requires KYLAS_API_KEY.0stars
Luma Eventsalx1p/luma-cal-mcpDiscover events from Luma — search by category, city, distance, and keywords with calendar export0stars
Google Flightsandreacappelletti97/google-flights-mcpMCP server for Google Flights: search, price tracking, cabin comparison, emissions, and more.0stars