Is vllm-mlx safe to install?

Security audit of waybarrios/vllm-mlx · MCP Server by waybarrios · ★ 1.6k

✓ SAFE Basic audit · rule-based scan · 43 published rules

Yes — vllm-mlx passed AgentSkillsHub's rule-based security scan with no dangerous patterns detected. As with any third-party skill, confirm what credentials it requests before production use.

What it 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.

No dangerous patterns were detected: no credential exfiltration, no obfuscated downloads, no sandbox-escape attempts, no prompt-injection markers.

Audit summary

Security grade	✓ SAFE
Quality score	71/100
GitHub stars	1.6k
Language	Python
License	Apache-2.0
Last updated	2026-11-05

Check before you install

What credentials does it ask for, and where are they stored?
Is the maintainer identifiable and the repo actively maintained?
Read the install scripts and network calls before trusting it.

Run a live scan → Full details & install 5-dimension deep audit

Related MCP Server audits

Is rea safe? — SAFE · ★ 446.4k
Is ECC safe? — SAFE · ★ 299.8k
Is n8n safe? — SAFE · ★ 209.9k
Is dify safe? — SAFE · ★ 160.8k
Is open-webui safe? — SAFE · ★ 157.6k
Is cc-switch safe? — SAFE · ★ 153.0k

Browse all MCP Server skills →

This is AgentSkillsHub's free basic audit: an automated rule-based scan with 43 published rules built on SlowMist's agent-security taxonomy (credential theft, obfuscated payloads, privilege escalation, covert instructions to the agent, and more), applied the same way to every open-source AI agent skill and MCP server we grade and refreshed every 8 hours. A SAFE grade is a scan result, not a guarantee — deep 5-dimension audits (code · credentials · vendor · supply-chain · operational) are available for enterprise. Audited: 2026-11-09.