vllm-mlx

OpenAI and Anthropic compatible server for Apple Silicon. Run LLMs and vision-language models (Llama, Qwen-VL, LLaVA) with continuous batching, MCP tool calling, and multimodal support. Native MLX backend, 400+ tok/s. Works with Claude Code.

{
  "mcpServers": {
    "vllm-mlx": {
      "command": "uvx",
      "args": [
        "vllm-mlx"
      ]
    }
  }
}

claude mcp add vllm-mlx uvx vllm-mlx

{
  "mcpServers": {
    "vllm-mlx": {
      "command": "uvx",
      "args": [
        "vllm-mlx"
      ]
    }
  }
}