vllm-mlx — security grade SAFE, quality 71/100

Security audit verdict: SAFE · quality 71/100

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 waybarrios · MCP Server · ★ 1.6k

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is vllm-mlx safe to install? View the security audit →

About vllm-mlx

vLLM-MLX vLLM-like inference for Apple Silicon - GPU-accelerated Text, Image, Video & Audio on Mac Overview vllm-mlx brings native Apple Silicon GPU acceleration to vLLM by integrating: MLX: Apple's ML framework with unified memory and Metal kernels mlx-lm: Optimized LLM inference with KV cache and quantization mlx-vlm: Vision-language models for multimodal inference mlx-audio: Speech-to-Text and Text-to-Speech with native voices mlx-embeddings: Text embeddings for semantic search and RAG Features Multimodal - Text, Image, Video & Audio in one platform Native GPU acceleration on Apple Silicon (M1, M2, M3, M4) Native TTS voices - Spanish, French, Chinese, Japanese + 5 more languages OpenAI API compatible - drop-in replacement for OpenAI client Anthropic Messages API - native /v1/me

anthropicanthropic-apiapple-siliconclaude-codecontinuous-batchinginference-serverllmlocal-llmmacosmcp

Quick Facts

Stars1,587
Forks222
LanguagePython
CategoryMCP Server
LicenseApache-2.0
Quality Score70.9665687613498/100
Open Issues121
Last Updated2026-09-19
Created2025-12-06
Platformsclaude-code, mcp, python
Est. Tokens~16k

Compatible Skills

These tools work well together with vllm-mlx for enhanced workflows:

  • mlx-omni-server — semantic(0.33)+complementary+shared_fw(openai)+rare_topics+same_lang+similar_pop+shared_platform (78%)
  • Toolio — semantic(0.29)+complementary+rare_topics+same_lang+similar_pop+shared_platform (64%)
  • claude-stt — semantic(0.24)+complementary+rare_topics+same_lang+similar_pop+shared_platform (62%)
  • mlx-llm — semantic(0.36)+complementary+rare_topics+same_lang+similar_pop+shared_platform (62%)
  • PyVision — semantic(0.23)+complementary+rare_topics+same_lang+similar_pop+shared_platform (62%)

vllm-mlx alternative? Top 6 similar tools

Looking for a vllm-mlx alternative? If you're comparing vllm-mlx 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.

  • mlx-serve by ddalcu · ⭐ 1.5k

    Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Includes MLX Core

  • claude-code-local by nicedreamzapp · ⭐ 3.3k

    Run Claude Code 100% on-device with local AI on Apple Silicon. MLX-native Anthropic-API server. 6 fighters inc

  • smg by lightseekorg · ⭐ 424

    Engine-agnostic LLM gateway in Rust. Full OpenAI & Anthropic API compatibility across vLLM, TRT-LLM, TokenSpee

  • axonhub by looplj · ⭐ 5.3k

    ⚡️ Open-source AI Gateway — Use any SDK to call 100+ LLMs. Built-in failover, load balancing, cost control & e

  • Unity-MCP by IvanMurzak · ⭐ 4.3k

    AI Skills, MCP Tools, and CLI for Unity Engine. Full AI develop and test loop. Use cli for quick setup. Effici

  • LightAgent by wanxingai · ⭐ 1.2k

    LightAgent: Lightweight Python framework for OpenAI-compatible agents with tools, memory, guardrails, tracing,

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

Frequently Asked Questions

What is vllm-mlx?

vllm-mlx is High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code support.. It is categorized as a MCP Server with 1.6k GitHub stars.

What programming language is vllm-mlx written in?

vllm-mlx is primarily written in Python. It covers topics such as anthropic, anthropic-api, apple-silicon.

How do I install or use vllm-mlx?

You can find installation instructions and usage details in the vllm-mlx GitHub repository at github.com/waybarrios/vllm-mlx. The project has 1.6k stars and 222 forks, indicating an active community.

What license does vllm-mlx use?

vllm-mlx is released under the Apache-2.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to vllm-mlx?

The top alternatives to vllm-mlx on Agent Skills Hub include mlx-serve, claude-code-local, smg. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

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:

View on GitHub → Browse MCP Server tools