No sign-up11,173 open-source and SaaS tools, with GitHub stats refreshed every day.

Webclaw

SaaS

Web scraping API that turns public pages into Markdown or structured JSON for AI agents, with an MCP server, a CLI and a self-hostable open-source core.

About Webclaw

Webclaw extracts public web pages into Markdown, JSON, plain text or raw HTML for LLMs and AI agents. You send a URL and get readable content back, with navigation, scripts and cookie banners stripped out, and JavaScript rendering and protected-page handling attempted by the API. Beyond scraping it offers search, map, crawl, monitor, extract, research and batch operations, and a structured extraction mode for requesting specific fields.

It can be used as a hosted REST API, a CLI or an MCP server with 12 tools that works in Claude, Cursor, Windsurf, Codex and other MCP clients. For teams moving from Firecrawl, v2 scrape, crawl and search routes are offered in a compatible form to ease migration. An agent can set itself up by reading an instruction file and receiving a scoped key after you approve it once in the browser.

The core is an AGPL-3.0 Rust project that can be self-hosted, with a CLI, REST server and MCP server running on your own hardware without hosted credits. Typical uses are feeding RAG pipelines, giving agents live web access, watching prices and stock, and deep research.

Key features

  • Markdown, JSON, plain text and raw HTML output
  • Scrape, crawl, search, map and monitor endpoints
  • MCP server with 12 tools
  • LLM mode that strips page clutter
  • JavaScript rendering and protected-page handling
  • Firecrawl-compatible v2 routes
  • Self-hostable AGPL-3.0 Rust core

Good fit for

  • Feeding clean web content into RAG pipelines
  • Letting agents watch prices and stock levels
Tags
web-scraping
api
mcp
llm
ai-agents
markdown
open-source
self-hosted

Webclaw: questions and answers

What is Webclaw used for?
Webclaw is a web scraping API that turns public pages into Markdown or structured JSON for AI agents, with an MCP server, a CLI and a self-hostable open-source core. It is a good fit for feeding clean web content into RAG pipelines, and letting agents watch prices and stock levels.
Is Webclaw free?
Yes. Webclaw has a free plan. Free plan gives 500 credits a month, and the open-source core can be self-hosted for free. Paid plans cost $19, $49, $99 and $399 per month; Dedicated is by arrangement.
Is Webclaw open source?
No. Webclaw is proprietary (closed-source) software. In the API Tools category, open-source options include Nango, CodeChat and Voiden.
Can I self-host Webclaw?
Yes. Although Webclaw is closed source, it can be self-hosted on your own servers, and the vendor also offers a hosted version.
What are some alternatives to Webclaw?
Webclaw competes with Jina AI, ScrapingBee and ScraperAPI.

Open-source alternatives to Webclaw

See all

SaaS alternatives to Webclaw

See all