Skip to content
mcp/harbor
Grok

humane proxy for Grok

io.github.vishisht16/humane-proxy

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

client:Grok transport:stdio runtime:pypi

Install humane proxy in Grok

.mcp.json (in your project root)

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

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

Grok Build reads Claude Code's .mcp.json and Claude Desktop's config unchanged, so a server you have already set up there needs nothing new. The Grok web app and X integration do not take custom servers. Grok docs

humane proxy in other clients

humane proxy MCP server