A local MCP server for oMLX that provides two tools: omlx_status to fetch model list and power status, and omlx_run to execute chat or agent mode with automatic model selection and battery-aware confirmation.
Enables image analysis and recognition through multiple LLM vision models (Gemini, GPT-4o, Qwen-VL, Doubao) by accepting image URLs or Base64 data and returning text descriptions or answers to questions about the images.