Skip to content
mcp/harbor
LangChain

rag for LangChain

io.github.fieldcure/rag

MCP RAG server with hybrid search, multi-KB support, and AI-powered chunk contextualization.

client:LangChain transport:stdio runtime:nuget

Install rag in LangChain

pip install langchain-mcp-adapters 

from langchain_mcp_adapters.client import MultiServerMCPClient

client = MultiServerMCPClient({
        "rag": {
            "transport": "stdio",
            "command": "dnx",
            "args": ["FieldCure.Mcp.Rag", "--yes"],
        }
})

tools = await client.get_tools()

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

rag in other clients

rag MCP server