io.github.Vishisht16/humane-proxy
Quality Score
80
/100
AI safety middleware — detects self-harm and criminal intent in LLM prompts.
§01 Install
Claude Desktop (uvx)
{
"mcpServers": {
"humane-proxy": {
"command": "uvx",
"args": [
"humane-proxy"
],
"env": {
"OPENAI_API_KEY": "<your-openai_api_key>",
"GROQ_API_KEY": "<your-groq_api_key>"
}
}
}
}§02 Environment variables
OPENAI_API_KEYsecret
OpenAI API key for Stage 3 reasoning (optional)
GROQ_API_KEYsecret
Groq API key for LlamaGuard Stage 3 (optional)
§03 MCP Quality Score · methodology
freshness
25
completeness
10
installability
25
documentation
15
stability
5
§04 Alternatives in AI & LLMs
OpenAI Tools MCP Server
ai.com.mcp/openai-tools
Focused MCP server for OpenAI image/audio generation (v2.0.0). Wraps endpoints via HAPI CLI.
ai.llmse/mcp
ai.llmse/mcp
Public MCP server for the LLM Search Engine
Perplexity API Platform
ai.perplexity/mcp-server
Real-time web search, reasoning, and research through Perplexity's API