omlx

LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar

18,558 stars Python 1 file · ~4,142 tokens #apple-silicon #inference-server #llm #macos #mlx #openai-api

omlx MCP Server

MCP server for jundot/omlx

Ready-to-Use Client Configurations

{
  "mcpServers": {
    "omlx": {
      "command": "npx",
      "args": [
        "-y",
        "@jundot/omlx"
      ]
    }
  }
}

{
  "mcpServers": {
    "omlx": {
      "command": "npx",
      "args": [
        "-y",
        "@jundot/omlx"
      ]
    }
  }
}

{
  "mcpServers": {
    "omlx": {
      "command": "npx",
      "args": [
        "-y",
        "@jundot/omlx"
      ]
    }
  }
}

{
  "mcpServers": {
    "omlx": {
      "command": "npx",
      "args": [
        "-y",
        "@jundot/omlx"
      ],
      "disabled": false,
      "autoApprove": []
    }
  }
}

{
  "mcpServers": {
    "omlx": {
      "command": "npx",
      "args": [
        "-y",
        "@jundot/omlx"
      ]
    }
  }
}

docker run -i --rm mcp/omlx