io.github.Vishisht16

humane-proxy

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

stdiocommunityinfra

Package Details

humane-proxy

0.2.2•https://pypi.org/project/humane-proxy

Transportstdio

Package Arguments

Positional

command

mcp-serve

Environment Variables

OPENAI_API_KEY

Secret

OpenAI API key for Stage 3 reasoning (optional)

GROQ_API_KEY

Secret

Groq API key for LlamaGuard Stage 3 (optional)