redaction for LangChain
one.secureai/redaction
Takes the people out of text before a model sees it, and puts them back in the reply.
client:LangChain
transport:streamable-http
Install redaction in LangChain
pip install langchain-mcp-adapters
from langchain_mcp_adapters.client import MultiServerMCPClient
client = MultiServerMCPClient({
"redaction": {
"transport": "streamable_http",
"url": "https://secureai.one/mcp",
}
})
tools = await client.get_tools()
get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs