LLM-ready output
Clean markdown, JSON, text and an LLM-optimized format that cuts token count ~90% vs raw HTML.
The platform
Webclaw is one Rust extraction engine, served as a hosted Cloud API, a single-binary CLI, and an MCP server for AI agents. Same clean, LLM-ready output everywhere, with SDKs for Python, TypeScript and Go.
Whether you call the API, the CLI, or the MCP server, the same Rust extraction pipeline does the work, so the output and the behavior are identical across all three.
Clean markdown, JSON, text and an LLM-optimized format that cuts token count ~90% vs raw HTML.
Challenge pages, CAPTCHAs and fingerprinting cleared transparently, no per-site config.
Sub-200ms median on static pages; JS rendering only kicks in when a page actually needs it.
Markdown, JSON, text, links, raw HTML, screenshots and more, requested per call.
A single fast engine under every surface, no headless browser fleet to babysit.
AGPL-3.0. Run the API, CLI and MCP server on your own hardware with no limits.
Type-safe clients over the same REST API, so you can call every endpoint in the language you already ship in.
Cancel anytime. API, CLI, or MCP, the engine is the same.
Cookies & analytics
We'd like to use analytics to understand how this site is used. Nothing loads or fires until you agree. See our privacy policy for the full list of processors.