webclaw
webclaw is an MCP server, listed under browser & scraping. It reaches webclaw. It needs WEBCLAW_API_KEY to authenticate. Its repository has 2,386 GitHub stars and is licensed under AGPL-3.0; we last read it on 2026-10-23.
Extracts structured web content for language models using Rust. Requires no external credentials and offers command-line, REST API, and MCP server interfaces.
Install
Read from webclaw’s own README, close to verbatim -- not written by us, and not guessed.
npx create-webclaw
What it reaches, and what it needs
Maintenance
Fast, local-first web content extraction for LLMs. Scrape, crawl, extract structured data — all from Rust. CLI, REST API, and MCP server.
What webclaw can do
10 tools documented in its README. An AI client calls these by name.
scrape- Extract one URL as markdown, text, JSON, LLM format, or HTML
crawl- Follow same-origin links and extract discovered pages
map- Discover URLs without extracting every page
batch- Scrape multiple URLs in parallel
extract- Convert page content into structured data
summarize- Summarize a page
diff- Compare page content snapshots
brand- Extract colors, fonts, logos, and metadata
search- Search the web and scrape results
research- Multi-source research workflow
Read from the README; names are kept only if the README contains them.
webclaw compared with similar servers
| Server | Reaches | Needs | Stars | Last update | Licence |
|---|---|---|---|---|---|
| webclaw (this page) | webclaw | WEBCLAW_API_KEY | 2,386 | 2026-10-21 | AGPL-3.0 |
| mcp-chrome | chrome | None listed | 12,501 | 2026-01-06 | MIT |
| fetcher-mcp | playwright | None listed | 1,088 | 2026-01-14 | MIT |
| puppeteer-mcp-server | chrome, puppeteer | None listed | 486 | 2025-03-14 | MIT |
| moling | — | None listed | 339 | 2026-03-15 | Apache-2.0 |
| MCP-Server-Playwright | playwright | None listed | 297 | 2025-06-05 | MIT |
Ranked by services in common with webclaw, then by stars. Figures are from each repository when we last read it.
Common questions about webclaw
- What does webclaw do?
- Extracts structured web content for language models using Rust. Requires no external credentials and offers command-line, REST API, and MCP server interfaces.
- How do I install webclaw?
- Its own README gives this command: npx create-webclaw. Run it where your MCP client can launch the server, and check the README for any settings it asks for.
- What does webclaw connect to, and what does it need?
- It reaches webclaw. The credentials we found in its source are WEBCLAW_API_KEY.
- Is webclaw official and is it maintained?
- We found nothing naming it as a vendor’s official server. Its repository has 2,386 GitHub stars and its state in our directory is listed. Its last commit we recorded was on 2026-10-21.
- What licence does webclaw use?
- The repository declares the AGPL-3.0 licence.
More MCP servers for browser & scraping
- mcp-chrome12,501 stars
- fetcher-mcp1,088 stars
- puppeteer-mcp-server486 stars
- moling339 stars
- MCP-Server-Playwright297 stars
- safari-mcp223 stars