@just-every/mcp-read-website-fast

by just-every · v1.0.0 · prompt

A fast, token-efficient web content extractor that converts web pages to clean Markdown. Designed for LLM/RAG pipelines, it provides both CLI and MCP server interfaces with smart caching, polite crawl

Install

Add @just-every/mcp-read-website-fast to Claude Code with the PolySkill CLI: polyskill add @just-every/mcp-read-website-fast

Instructions

# CLAUDE.md This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository. ## Project Overview A fast, token-efficient web content extractor that converts web pages to clean Markdown. Designed for LLM/RAG pipelines, it provides both CLI and MCP server interfaces with smart caching, polite crawling, and minimal dependencies. ## Core Modules & Files - `src/crawler/`: URL fetching, robots.txt respect, queue management - `src/parser/`: Readability extraction, HTML to Markdown conversion - `src/cache/`: SHA-256 based file caching system - `src/internal/fetch…

Keywords: github, web-content-extraction, markdown-converter, llm-integration, data-crawling, cli-tool, mcp-server, token-efficient, smart-caching