No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by jjang-ai · MCP Server · ★ 861
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is vmlx safe to install? View the security audit →
MLX Inference Server for Apple Silicon Self-hosted inference server for LLMs, VLMs, and image generation on Apple Silicon. OpenAI + Anthropic + Ollama compatible HTTP API. Self-hosted; no third-party API keys required. Native MTP artifact detection and family-specific cache policy gates keep speculative/cache settings explicit and model-safe. Looking for a native Swift macOS app or Swift inference engine? See osaurus.ai. <img src="htt
| Stars | 861 |
| Forks | 89 |
| Language | Python |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 69.8626744920228/100 |
| Open Issues | 47 |
| Last Updated | 2026-09-19 |
| Created | 2026-02-18 |
| Platforms | mcp, python |
| Est. Tokens | ~21k |
These tools work well together with vmlx for enhanced workflows:
Looking for a vmlx alternative? If you're comparing vmlx with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuou
Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Includes MLX Core
gemini drawing MCP & skill through browser, can be used in openclaw or any agent that supports MCP. Gemini画图 M
Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server
'afm' command cli: macOS server and single prompt mode that exposes Apple's Foundation and MLX Models and othe
Local-first persistent agentic memory powered by Recursive Memory Harness (RMH). Open source must win.
Explore other popular mcp server tools:
vmlx is vMLX - Use MLX models easily - JANGQ (GGUF for MLX) - Not dependant on mlx_vlm. It is categorized as a MCP Server with 861 GitHub stars.
vmlx is primarily written in Python. It covers topics such as anthropic-api, kvcache-compression, kvcache-optimization.
You can find installation instructions and usage details in the vmlx GitHub repository at github.com/jjang-ai/vmlx. The project has 861 stars and 89 forks, indicating an active community.
vmlx is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to vmlx on Agent Skills Hub include vllm-mlx, mlx-serve, gemini-skill. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: