Local LLM Guard for Ollama / llama.cpp for Claude Desktop

io.github.aiops-tools/ai-guardian

Governed local-LLM observability: model policy, prompt scanner, capture proxy, 21 tools.

client:Claude Desktop transport:stdio runtime:pypi

Install Local LLM Guard for Ollama / llama.cpp in Claude Desktop

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

{
  "mcpServers": {
    "ai-guardian": {
      "command": "uvx",
      "args": [
        "ai-guardian-aiops"
      ]
    }
  }
}

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