io.github.DevsHero/shadow-crawlweb-automation

ShadowCrawl

Verified · yesterday

Stealth scraping & search. Bypasses Cloudflare, DataDome & LinkedIn via Cyborg HITL approach.

Install

claude mcp add --transport http shadow-crawl https://shadowcrawl--devshero.run.tools

Our take

Self-hosted Rust binary for web search, extraction, and stateful browser automation with explicit anti-bot bypass (CDP rendering, proxy rotation, human-in-the-loop CAPTCHA solving). Technically substantial and honestly documented, but its headline capability — defeating Cloudflare/DataDome and scraping auth-walled sites — violates most target sites' ToS, so treat it as a liability decision, not just a tool choice. Note the project has been rebranded to CortexScout (repo renamed cortex-scout) and last push was ~a month ago. For self-hosters doing research scraping who accept the legal exposure.

reviewed by hand · 2026-07-05

Something wrong or dead here? Report it

Verification record

last verified: yesterday
github stars: 68
last commit: 29 days ago
archived: no
license: MIT
in registry since: 2026-02-14

github.com/DevsHero/ShadowCrawl