</>MCP Agents Market
MCP Server

webclaw

by 0xMassi2.3kRustUpdated 2026-08-30

Fast, local-first web content extraction for LLMs. Scrape, crawl, extract structured data — all from Rust. CLI, REST API, and MCP server.

Claude CodeClaude DesktopCursorWindsurfOpenCodeCodex CLI

Webclaw is a web content extraction tool built in Rust that turns websites into clean markdown, structured JSON, and LLM-ready text. It offers a CLI, REST API, and MCP server that integrates with Claude Desktop, Claude Code, Cursor, Windsurf, and other MCP-compatible AI tools. Developers can scrape single pages, crawl entire sites, extract structured data, compare page changes over time, and pull brand assets—all with local-first processing that doesn't require API keys for most sites. The tool also ships as an installable skill for MCP agents and provides TypeScript, Python, and Go SDKs for programmatic access.

Key Features

MCP server for Claude Desktop, Claude Code, Cursor, Windsurf, and other MCP clients with zero-install npx launcher
Local-first extraction engine that converts HTML to markdown, plain text, JSON, LLM-optimized format, or cleaned HTML
Site crawling with configurable depth and page limits, plus URL mapping without full content extraction
CSS selector-based content filtering to include or exclude specific page elements
Structured data extraction, page summarization, and diff comparison using local or configured LLMs
Brand asset extraction (colors, fonts, logos, metadata) and web search integration
Batch scraping for parallel processing of multiple URLs
Optional hosted API for JavaScript rendering, bot-protected sites, and async crawl jobs

Use Cases

  • 01Give AI agents clean web content by integrating the MCP server with Claude, Cursor, or other assistants
  • 02Prepare documentation sites, blogs, and help centers for RAG ingestion pipelines
  • 03Monitor competitor pricing pages, changelogs, and product documentation for changes
  • 04Extract structured data from messy web pages for automation workflows
  • 05Crawl and summarize research sources with multi-page citation support
  • 06Collect brand intelligence including logos, color palettes, fonts, and social metadata

Related MCP Servers

View more

webclaw — FAQ

What is webclaw?+

Webclaw is a Rust-based web scraping and extraction tool that converts websites into clean markdown, JSON, or LLM-ready text. It provides a CLI, MCP server for AI agents, REST API, and SDKs, with most features running locally without API keys.

How do I install webclaw for Claude Desktop or Claude Code?+

Run 'npx create-webclaw' to auto-detect your MCP-compatible clients and configure them automatically. Alternatively, add the MCP server manually by pointing your client config at 'npx -y @webclaw/mcp'.

Which AI clients work with webclaw?+

Webclaw's MCP server works with Claude Code, Claude Desktop, Cursor, Windsurf, OpenCode, Codex CLI, and other MCP-compatible tools. It can also be added as a skill to agents that support the skills.sh format.

Do I need an API key to use webclaw?+

No API key is required for local extraction of most sites. Set WEBCLAW_API_KEY only when you need the hosted API for JavaScript rendering, bot-protected pages, web search, or async crawl jobs.

Is webclaw free and open source?+

Yes, webclaw is open source under the AGPL-3.0 license. The CLI and MCP server are free to use locally. A hosted API at webclaw.io is available for features like JavaScript rendering and web search.

What are the prerequisites for building webclaw from source?+

Building from source requires Rust toolchain and native build tools: pkg-config, OpenSSL, CMake, Clang, and Git. On macOS run 'xcode-select --install'; on Debian/Ubuntu install pkg-config, libssl-dev, cmake, clang, git, and build-essential.

How do I install webclaw?+

Open the source repository on GitHub and follow its README. webclaw is a mcp server — MCP Agents Market links you directly to the official repo.

Is webclaw free?+

webclaw is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.

Related searches