RAG for your documents for LangChain
io.github.devilsdev/rag-mcp-server
Search a folder of documents and check answers against them. Offline: no API key or database.
client:LangChain
transport:stdio
runtime:npm
Install RAG for your documents in LangChain
pip install langchain-mcp-adapters
from langchain_mcp_adapters.client import MultiServerMCPClient
client = MultiServerMCPClient({
"rag-mcp-server": {
"transport": "stdio",
"command": "npx",
"args": ["-y", "@devilsdev/rag-mcp-server"],
}
})
tools = await client.get_tools()
get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs