Skip to content
mcp/harbor
LangChain

rag-mcp for LangChain

io.github.masihmoafi/rag-mcp

Scoped hybrid search (BM25, embeddings, reranking) and grounded answers over local files and folders

client:LangChain transport:stdio runtime:pypi

Install rag-mcp in LangChain

pip install langchain-mcp-adapters 

from langchain_mcp_adapters.client import MultiServerMCPClient

client = MultiServerMCPClient({
        "rag-mcp": {
            "transport": "stdio",
            "command": "uvx",
            "args": ["ragmcp-cli"],
        }
})

tools = await client.get_tools()

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

rag-mcp in other clients

rag-mcp MCP server