io.github.77777R7/octocrawlweb-automation

octocrawl

Verified · today

Web scraper for agents: blocked, empty and wrong pages reported as such, with an Evidence Record.

Install

claude mcp add --transport http octocrawl https://mcp.octocrawl.dev/mcp

Our take

Octocrawl is a web-scraping MCP server that emphasizes explicit reporting of blocked, empty, or incorrect pages with an evidence record. It is useful for agents that need auditable web extraction rather than silent scrape failures, and its npm usage is noticeable for a new project despite no visible GitHub stars.

reviewed by hand · 2026-10-10

Something wrong or dead here? Report it

Verification record

last verified
today
github stars
0
last commit
today
archived
no
license
AGPL-3.0
npm
@octocrawl/mcp
downloads / wk
364
latest version
0.3.2
in registry since
2026-10-09

github.com/77777R7/Octocrawl

More in web-automation

browse all →
browser-useweb-automation

browser-use

Verified · yesterday

Control a real Chrome browser to complete any task: fill forms, extract data, book flights.

hand-reviewed117k starschecked yesterday

Scraplingweb-automation

Scrapling MCP Server

Verified · 32 days ago

Web scraping with stealth HTTP, real browsers, and Cloudflare bypass. CSS selectors supported.

hand-reviewed79k starschecked 32 days ago

playwright-mcpweb-automation

playwright-mcp

Verified · 34 days ago

Playwright Tools for MCP

hand-reviewed37k stars5.9m dl/wkchecked 34 days ago

invisible-playwright-mcpweb-automation

invisible_playwright_mcp

Verified · 16 days ago

AI browser agent: browses, clicks, types, and reads real web pages from plain-English instructions.

hand-reviewed32k starschecked 16 days ago

aihawkweb-automation

AIHawk

Verified · 27 days ago

AI browser agent: browses, clicks, types, and reads real web pages from plain-English instructions.

hand-reviewed30k starschecked 27 days ago