Webclaw is a Rust-based CLI, MCP server, and REST API for turning web pages into clean markdown, JSON, and LLM-ready context. It supports local extraction with optional hosted API and various output formats.
Collecting history — the radar snapshots this repo daily. The trend line appears after 3 days of data (1 so far).
What it is
webclaw is a tool that turns websites into clean markdown, JSON, and LLM-ready context. It provides a CLI, an MCP server, an extraction engine, and a self-hostable server, enabling local-first web content extraction for LLMs.
How it works
The project contains multiple crates: webclaw-core for extraction logic, webclaw-fetch for fetching/crawling, webclaw-llm for LLM provider support, webclaw-pdf for PDF extraction, webclaw-mcp for MCP server, and webclaw-cli for the command-line interface. The core logic outputs markdown, text, JSON, and LLM-ready formats, with local processing and optional hosted API usage. The MCP integration allows agents to issue scrape, crawl, map, and related actions via MCP.
Getting started
Install options include:
npx create-webclaw
brew tap 0xMassi/webclaw
brew install webclaw
docker run --rm ghcr.io/0xmassi/webclaw https://example.com
cargo install --git https://github.com/0xMassi/webclaw.git webclaw-cli
cargo install --git https://github.com/0xMassi/webclaw.git webclaw-mcp
If building from source, follow platform prerequisites listed in the README.
Quick start examples:
webclaw https://stripe.com --format markdown
webclaw https://docs.anthropic.com --format llm
webclaw https://example.com/blog/post --only-main-content
webclaw https://docs.rust-lang.org --crawl --depth 2 --max-pages 50
There is also an MCP server setup with an example npx launcher:
{ "mcpServers": { "webclaw": { "command": "npx", "args": ["-y", "@webclaw/mcp"] } } }
Recent releases
Latest releases include v0.6.16 (2026-07-22), v0.6.15 (2026-07-18), v0.6.14 (2026-06-27), v0.6.13 (2026-06-17), and v0.6.12 (2026-06-17) with changes around server descriptions, sponsor removals, documentation updates, and hot-path speed improvements.
Full changelog: https://github.com/0x
Traction
Stars: 2105, Forks: 210
Behind the repo
Strategic and infrastructure partners include SerpApi for web search API and ColdProxy for proxy infrastructure; NodeMaven and MangoProxy are listed as studio partners.
Caveats
License: AGPL-3.0. Creation date: 2026-03-10. Last push: 2026-08-03. Open issues: 2. Configuration variables include WEBCLAW_API_KEY, LLM provider keys, and proxy settings.