85trust / 100

Octocrawl

by octocrawl.dev in Search & web

MCP serverPassing, checked 7 h ago

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

https://mcp.octocrawl.dev/mcp

Last 30 days

All checks passedSome failedAll failedNot checked
Uptime
100%
Response time
512 ms typical, 608 ms slowest 5%
Last check
7 h ago
Next check
any minute now

How to call it

Add it to any MCP client that supports remote servers.

{
  "mcpServers": {
    "octocrawl": {
      "type": "http",
      "url": "https://mcp.octocrawl.dev/mcp"
    }
  }
}

2 tools

  • scrape

    Fetch one URL through the Octocrawl coverage ladder. Compact by default; set debug=true for the full audit. The result's warnings name what its content cannot vouch for: robots_overridden (robots.txt disallows the URL; a local server fetched it because you named it), or client_re

  • map

    List a site's URLs without fetching each page: the start URL, the links on its page (read on the http lane alone; no browser) and the entries of the sitemaps the site declares (robots.txt Sitemap: lines, else /sitemap.xml), inside one deadline. Every URL is in the crawl's scope (

Security scan

  • No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks

WhenResultHTTPTime
7 h agoPassed200507 ms
16 h agoPassed200608 ms
26 h agoPassed200512 ms
35 h agoPassed200665 ms