Website Crawler — Markdown Pages, Sitemaps & RAG Provenance for LangChain
io.github.kriton-dev/website-to-markdown
Crawl sites to Markdown with sitemaps, globs and depth limits, obeying robots and crawl-delay
client:LangChain
transport:streamable-http
Install Website Crawler — Markdown Pages, Sitemaps & RAG Provenance in LangChain
pip install langchain-mcp-adapters
from langchain_mcp_adapters.client import MultiServerMCPClient
client = MultiServerMCPClient({
"website-to-markdown": {
"transport": "streamable_http",
"url": "https://mcp.apify.com/?tools=hermeskd/website-to-markdown",
}
})
tools = await client.get_tools()
get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs