Skip to content
mcp/harbor
LangChain

humane proxy for LangChain

io.github.vishisht16/humane-proxy

AI safety middleware — detects self-harm and criminal intent in LLM prompts.

client:LangChain transport:stdio runtime:pypi

Install humane proxy in LangChain

pip install langchain-mcp-adapters 

from langchain_mcp_adapters.client import MultiServerMCPClient

client = MultiServerMCPClient({
        "humane-proxy": {
            "transport": "stdio",
            "command": "uvx",
            "args": ["humane-proxy"],
        }
})

tools = await client.get_tools()

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

humane proxy in other clients

humane proxy MCP server