About webcrawl-mcp
webcrawl-mcp is an MCP server in the Scraping category: lightweight MCP server for web scraping, search, and crawling. Uses local trafilatura/DuckDuckGo by default with optional Firecrawl fallback for transport-blocked pages.
Install
git clone https://github.com/andyliszewski/webcrawl-mcpThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (4)
webcrawl_crawlBFS crawl multiple pages (each result includes provenance)
Parameters not published.
webcrawl_mapDiscover same-domain URLs from a starting page
Parameters not published.
webcrawl_scrapeFetch a single URL → `{content, source}` (markdown + provenance)
Parameters not published.
webcrawl_searchDuckDuckGo search (optionally scrape results, each with provenance)
Parameters not published.
Ask AI
Ask AI about webcrawl-mcp
Powered by Claude · Grounded in docs
Security checks
6 checks have not been run yet.