humane-proxy

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

GitHub · PyPI · Registry

Dev tools & GitHub AI models & media

Install

Run it directly:

uvx humane-proxy

Or add it to your client config (Claude Desktop claude_desktop_config.json, Cursor .cursor/mcp.json):

{
  "mcpServers": {
    "humane-proxy": {
      "command": "uvx",
      "args": [
        "humane-proxy"
      ]
    }
  }
}

Generated from the package metadata in the official MCP Registry. MCP Morning does not run or test servers; check required environment variables in the project README.

Alternatives