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 Azure-Samples · MCP Server · ★ 986
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is AI-Gateway safe to install? View the security audit →
✨ AI Gateway Labs Explore the enterprise-grade gateway for managing AI Models, Tools, and Agents Why AI Gateway? Building production-ready AI applications requires more than just calling model APIs. You need security, reliability, observability, and cost control—without slowing down innovation. AI Gateway powered by Azure API Management provides: 🔐 Security — OAuth 2.0, managed identities, content safety filtering ⚡ Performance — Load balancing, semantic caching, request routing 📊 Observab
| Stars | 986 |
| Forks | 514 |
| Language | Jupyter Notebook |
| Category | MCP Server |
| License | MIT |
| Quality Score | 66.170149117301/100 |
| Open Issues | 80 |
| Last Updated | 2026-09-16 |
| Created | 2024-04-03 |
| Platforms | mcp |
| Est. Tokens | ~18k |
Looking for a AI-Gateway alternative? If you're comparing AI-Gateway 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.
Enterprise AI Platform with guardrails, MCP registry, gateway & orchestrator
Skills, MCP servers, Custom Agents, Agents.md for SDKs to ground Coding Agents
A set of tools that gives agents powerful capabilities.
LightAgent: Lightweight Python framework for OpenAI-compatible agents with tools, memory, guardrails, tracing,
A middleware to provide an openAI compatible endpoint that can call MCP tools
Agent samples built using the Strands Agents SDK.
Explore other popular mcp server tools:
AI-Gateway is Labs to explore AI Models, MCP servers, and Agents with the AI Gateway powered by Azure API Management and Microsoft Foundry 🚀. It is categorized as a MCP Server with 986 GitHub stars.
AI-Gateway is primarily written in Jupyter Notebook. It covers topics such as a2a, agents, apimanagement.
You can find installation instructions and usage details in the AI-Gateway GitHub repository at github.com/Azure-Samples/AI-Gateway. The project has 986 stars and 514 forks, indicating an active community.
AI-Gateway is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to AI-Gateway on Agent Skills Hub include archestra, skills, tools. 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: