web content extractor for LangChain
io.github.agenson-horrowitz/web-content-extractor
Extract and process web content into clean, structured formats optimized for LLMs.
client:LangChain
transport:stdio
runtime:npm
Install web content extractor in LangChain
pip install langchain-mcp-adapters
from langchain_mcp_adapters.client import MultiServerMCPClient
client = MultiServerMCPClient({
"web-content-extractor": {
"transport": "stdio",
"command": "npx",
"args": ["-y", "@agenson-horrowitz/web-content-extractor-mcp"],
}
})
tools = await client.get_tools()
get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs