Read Website Fast

MCPOfficialOpen SourceMIT55.1

by just-every • Search & Retrieval

Converts web pages to clean, token-efficient Markdown for AI agents and local crawling workflows.

Example Use Cases

1
Convert a single web page into clean Markdown for downstream LLM processing with minimal token overhead.
2
Crawl a website (configurable depth and concurrency) while respecting robots.txt and preserving links for knowledge-graph construction.
3
Fast, local content extraction with caching and optional chunking to support IDE integrations and Claude Code workflows.

Description

This MCP server fetches web pages locally, strips noise using Mozilla Readability, converts HTML to Markdown with Turndown (GFM), and preserves links for knowledge graphs. It includes polite crawling (robots.txt, rate limiting), SHA-256 based caching, concurrent fetching, optional chunking, and a stream-first design for low memory and token usage. Built for fast startup and integration with Claude Code, IDEs, and LLM pipelines, it aims to make web content extraction efficient and developer-friendly.

Quick Actions

View on GitHub

Security

Scanned 3 month(s) ago

Risk Level

MINIMAL

Read-only data retrieval, no side effects

Trust Score

D44/100

4/17 checks passed

Scores are informational only and provided “as is” without warranty. AgentHotspot assumes no liability for actions taken based on these ratings.

Quick Stats

Service TypeMCP

Pricing ModelFree

Capabilities0 Tools / 0 Prompts / 0 Resources

Ownerjust-every

CategorySearch & Retrieval

DependenciesStandalone