Skip to content
LangChain

Fetch for LangChain

io.github.modelcontextprotocol/fetch

Reference server that fetches a URL and converts the page to markdown for a model to read, with optional raw mode and pagination through long pages.

client:LangChain transport:stdio runtime:pypi tools:1

Install Fetch in LangChain

pip install langchain-mcp-adapters

from langchain_mcp_adapters.client import MultiServerMCPClient

client = MultiServerMCPClient({
        "fetch": {
            "transport": "stdio",
            "command": "uvx",
            "args": ["mcp-server-fetch"],
        }
})

tools = await client.get_tools()

get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs

What LangChain can do once it is connected

Fetch in other clients