@agenson-tools
基本情報
Agent-optimized MCP server for extracting clean, structured content from web pages
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"web-content-extractor": {
"command": "npx",
"args": [
"@agenson-horrowitz/web-content-extractor-mcp"
]
}
}
}Extract clean article content from any URL as agent-optimized markdown. Uses advanced content extraction to get main article text, metadata, and reading stats. Perfect for agents processing news, blogs, documentation.
Extract structured data (tables, lists, key-value pairs) from any webpage as JSON. Perfect for agents that need to process data tables, pricing lists, feature comparisons, or any structured web content.
Get all links from a webpage with intelligent categorization and context. Returns internal/external links, link text, and destination context. Essential for agents doing competitive analysis, site mapping, or link discovery.
Take a screenshot of a webpage and convert visual layout to structured markdown description. Perfect for agents that need to understand page layout, UI elements, or visual content when text extraction is insufficient.
Process multiple URLs in parallel and return consolidated results. Highly efficient for agents that need to analyze multiple pages, compare content, or do batch research. Includes rate limiting and error recovery.
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.
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.
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.
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.
All data is extracted from provided URLs and returned in the tool response; no persistent storage on the server side is mentioned.
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.
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).
Official MCP server for BlazingCDN - AI agents (Claude, Cursor, Windsurf) manage CDN resources, purge cache, query metrics, domains, Anycast CDN, Video CDN and Media CDN
localscreenshot is a Website screenshot MCP server and API available at https://localscreenshot.com/api. Localscreenshot screenshot api turns any public web page into an image or a PDF. Take the capture from one of 227 c
Connect Claude Desktop to your ServiceNow PDI. Query records, inspect Business Rules, review ACLs, and troubleshoot against your live instance.
1,000+ fully localized prompt templates across 40+ categories. Compare Mode — send the same prompt to up to 9 AI providers (ChatGPT, Claude, Gemini, Grok, Groq, Copilot, Mistral, Perplexity, DuckDuckGo AI) and compare an
NetFoundry LLM Gateway is an OpenAI-compatible API proxy that routes requests across multiple LLM providers using zero-trust networking. Zero trust LLM gateway. OpenAI-compatible proxy with semantic routing and load bala
コメント