webclaw

A fast, locally-focused web content extraction tool supporting CLI, REST API, and MCP server.

MCPResearchOpen source

Type: MCP
Transport: stdio
Open source: Yes
GitHub Stars: ★ 1.5k
Source: mcp-github
Repository: github.com/0xMassi/webclaw

Overview

webclaw is a fast, locally-first web content extraction tool designed for LLMs. It can scrape, crawl, and extract structured data, with support for Rust implementation. Offers multiple access methods including CLI, REST API, and MCP server. With webclaw, AI can convert web pages into clean Markdown, JSON, or LLM-ready context. Ideal for scenarios requiring useful information extraction from web pages, such as document crawling and competitor analysis.

Capabilities

▪Scrape individual web pages
▪Crawl entire websites
▪Extract structured data
▪Generate LLM-optimized text
▪Retain only main content
▪Include or exclude specific selectors

Use cases

Document crawling and organizationCompetitor pricing page comparisonBrand asset extractionWeb content change monitoring

Setup

Requires: Node 环境

npx create-webclaw

This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.

FAQ

How to install webclaw?

Install quickly using `npx create-webclaw`.

What output formats does webclaw support?

Supports Markdown, JSON, LLM-optimized text, and more.

Related skills

Scrapling

An adaptive web scraping framework capable of handling everything from single requests to large-scale scraping.

MCP

TrendRadar

An AI-driven tool for sentiment monitoring and trend analysis, supporting multi-platform aggregation, RSS subscription, and intelligent notifications.

MCP