azure-aigateway

Installation
Summary

Govern AI models, MCP tools, and agents through Azure API Management with semantic caching, token limits, and content safety.

  • Supports five core policy categories: semantic caching (60-80% cost savings), token rate limiting, content safety filtering, jailbreak detection, and request rate limiting for MCP tool protection
  • Enables backend configuration for Azure OpenAI, AI Foundry models, and custom APIs with load balancing and managed identity authentication
  • Includes token metrics and observability for tracking AI usage and cost control across deployments
  • Provides quick commands to add backends, apply policies in recommended order, and test endpoints via gateway URL with subscription keys
SKILL.md

Azure AI Gateway

Configure Azure API Management (APIM) as an AI Gateway for governing AI models, MCP tools, and agents.

To deploy APIM, use the azure-prepare skill. See APIM deployment guide.

When to Use This Skill

Category Triggers
Model Governance "semantic caching", "token limits", "load balance AI", "track token usage"
Tool Governance "rate limit MCP", "protect my tools", "configure my tool", "convert API to MCP"
Agent Governance "content safety", "jailbreak detection", "filter harmful content"
Configuration "add Azure OpenAI backend", "configure my model", "add AI Foundry model"
Testing "test AI gateway", "call OpenAI through gateway"

Quick Reference

Related skills

More from microsoft/github-copilot-for-azure

Installs
GitHub Stars
207
First Seen
azure-aigateway — microsoft/github-copilot-for-azure