vllm-mlx
Level AMCP ecosystemNot an MCP ServerSourceHigh-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code support.
Overview
vllm-mlx is a high-performance inference server for Apple Silicon, built on native MLX and Metal and exposing both OpenAI- and Anthropic-compatible APIs from a single process. It offers continuous batching, paged KV cache, prefix caching, and SSD-tiered cache, and runs text, image, video, audio, and embedding models, with MCP tool calling, structured output, and reasoning extraction.
Installation
View source repo →Related servers
opencode-power-pack55 rigorous skills for Claude Code, Codex, OpenCode 1 and 2, and Pi: code reviewOmniRouteNever stop coding. Free MIT AI gateway: one endpoint, 375 providers (150+ free),OmniRouteNever stop coding. Free MIT AI gateway: one endpoint, 375 providers (150+ free),mcp-for-blenderCommunity plugin to control Blender 3D with any LLM of your choice. Not affiliatmastraMastra is the modern TypeScript framework for AI-powered applications and agentseditorOpen-source 3D architectural editor with a local CLI, MCP tools, and practical w