smg — security grade SAFE, quality 66/100

Security audit verdict: SAFE · quality 66/100

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 smg-project · MCP Server · ★ 543

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

🔒 Is smg safe to install? View the security audit →

About smg

Shepherd Model Gateway <img src="https://img.shields.io/badge/PyTorch-Technical%20Blog-EE4C2C?logo=pytor

anthropicanthropic-apichatclaudegeminiinference-gatewaylightseekllmmcpopenai

Quick Facts

Stars543
Forks171
LanguageRust
CategoryMCP Server
LicenseApache-2.0
Quality Score65.5385219087921/100
Open Issues105
Last Updated2026-09-23
Created2025-11-22
Platformsclaude-code, gemini, mcp, rust
Est. Tokens~23k

Compatible Skills

These tools work well together with smg for enhanced workflows:

  • smg — semantic(1.00)+shared_fw(anthropic,openai)+rare_topics+same_lang+similar_pop+shared_platform (91%)
  • token_proxy — semantic(0.36)+complementary+shared_fw(anthropic,openai)+same_lang+similar_pop+shared_platform (79%)
  • llm-rosetta — semantic(0.37)+complementary+shared_fw(anthropic,openai)+rare_topics+similar_pop+shared_platform (78%)
  • codex-app-transfer — semantic(0.35)+complementary+shared_fw(openai)+rare_topics+same_lang+similar_pop+shared_platform (75%)
  • anthropic-proxy-rs — semantic(0.17)+complementary+shared_fw(anthropic,openai)+same_lang+similar_pop+shared_platform (72%)

smg alternative? Top 6 similar tools

Looking for a smg alternative? If you're comparing smg 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.

  • smg by lightseekorg · ⭐ 424

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

  • chat.md by rusiaaman · ⭐ 155

    An md file as a chat interface and editable history in one.

  • vllm-mlx by waybarrios · ⭐ 1.6k

    High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuou

  • chat-js by FranciscoMoretti · ⭐ 1.2k

    Production-ready AI chat. Start here and make it your own. Formerly Sparka AI

  • py-gpt by szczyglis-dev · ⭐ 1.9k

    Desktop AI Assistant powered by GPT-6, GPT-5, Gemini, Claude, Ollama, Grok, DeepSeek, Perplexity, chat, agents

  • Risuai by kwaroran · ⭐ 1.7k

    Make your own story. User-friendly software for LLM roleplaying

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Rust Agent Tools

Frequently Asked Questions

What is smg?

smg is Engine-agnostic LLM gateway in Rust. Full OpenAI & Anthropic API compatibility across vLLM, TRT-LLM, TokenSpeed, SGLang, OpenAI, Gemini & more. Industry-first gRPC pipeline, KV cache-aware routing, ch. It is categorized as a MCP Server with 543 GitHub stars.

What programming language is smg written in?

smg is primarily written in Rust. It covers topics such as anthropic, anthropic-api, chat.

How do I install or use smg?

You can find installation instructions and usage details in the smg GitHub repository at github.com/smg-project/smg. The project has 543 stars and 171 forks, indicating an active community.

What license does smg use?

smg 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 smg?

The top alternatives to smg on Agent Skills Hub include smg, chat.md, vllm-mlx. 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