Skip to content
Claude Desktop

humane proxy for Claude Desktop

io.github.vishisht16/humane-proxy

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

client:Claude Desktop transport:stdio runtime:pypi

Install humane proxy in Claude Desktop

~/Library/Application Support/Claude/claude_desktop_config.json · windows: %APPDATA%\Claude\claude_desktop_config.json

Held in this page only — never stored, logged, or sent anywhere but back to your screen.

{
  "mcpServers": {
    "humane-proxy": {
      "command": "uvx",
      "args": [
        "humane-proxy"
      ],
      "env": {
        "OPENAI_API_KEY": "<OPENAI_API_KEY>",
        "GROQ_API_KEY": "<GROQ_API_KEY>"
      }
    }
  }
}

Settings → Developer → Edit Config opens this file. Restart the app after saving. Claude Desktop docs

humane proxy in other clients