docker-ai-stack

Deploy a complete, self-hosted AI stack on your own server with one command. Includes Ollama (LLM), LiteLLM (AI gateway), Whisper (STT), Kokoro (TTS), Embeddings (RAG), and MCP Gateway. Most services run locally; LiteLLM optionally routes to external providers. Supports NVIDIA GPU (CUDA) acceleration.

{
  "mcpServers": {
    "docker-ai-stack": {
      "command": "npx",
      "args": [
        "-y",
        "hwdsl2/docker-ai-stack"
      ]
    }
  }
}

claude mcp add docker-ai-stack npx -y hwdsl2/docker-ai-stack

{
  "mcpServers": {
    "docker-ai-stack": {
      "command": "npx",
      "args": [
        "-y",
        "hwdsl2/docker-ai-stack"
      ]
    }
  }
}