azure-aigateway
Configure Azure API Management (APIM) as AI Gateway to secure, observe, control AI models, MCP servers, agents. Helps with rate limiting, semantic caching, content safety, load balancing. USE FOR: AI Gateway, APIM, setup gateway, configure gateway, add gateway, model gateway, MCP server, rate limit, token limit, semantic cache, content safety, load balance, OpenAPI import, convert API to MCP. DO NOT USE FOR: deploy models (use microsoft-foundry), Azure Functions (use azure-functions), databases (use azure-postgres).
npx skills add majiayu000/claude-skill-registry --skill azure-aigateway --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Bootstrap and configure Azure API Management (APIM) as an AI Gateway for securing, observing, and controlling AI models, tools (MCP Servers), and agents.
How it works
- Provides security via authentication, authorization, and content safety.
- Enables observability through token metrics, logging, and monitoring.
- Offers control with rate limiting, token limits, and load balancing.
- Optimizes costs/latency with semantic caching.
- Includes specific patterns for quick bootstrap, semantic caching, token rate limiting, content safety, MCP/tool rate limits, managed identity auth, load balancing with retry, adding AI Foundry models behind gateway (step-by-step), importing APIs from OpenAPI, and converting APIs to MCPs.
- Details include Bicep/az CLI snippets, policy XML templates, and examples for deploying APIM, configuring backends, and applying policies.
When to use it
Use when asked to set up or modify a gateway for AI models, tools, agents; add a gateway to an MCP server; enable rate limiting, token limits, semantic caching, content safety; import APIs from OpenAPI; or convert APIs to MCP. Trigger phrases and scenarios are provided in the skill activation triggers.
What it can touch
- Backend configurations for AI Foundry, OpenAI, and other backends via az apim backend create.
- APIM services and instances via az group, az deployment group, and az apim commands.
- API imports and updates via az apim api import/update.
- Policy definitions in XML/Inline to implement caching, rate limiting, content safety, and authentication.
- Bicep templates for bootstrapping APIM configurations.
- Commands and environment setup for discovering and deploying AI Foundry models, and linking them as backends.
Caveats
- Default SKU recommendation is Basicv2 for cost and speed considerations.
- Do not deploy models directly through APIM; use designated services (e.g., microsoft-foundry) as specified.
- Follow the exact command names, resource identifiers, and parameters as shown in the skill; no deviations or assumptions beyond what's described.
# Azure AI Gateway Bootstrap and configure Azure API Management (APIM) as an AI Gateway for securing, observing, and controlling AI models, tools (MCP Servers), and agents. ## Skill Activation Triggers **Use this skill immediately when the user asks to:** - "Set up a gateway for my model" - "Set up a gateway for my tools" - "Set up a gateway for my agents" - "Add a gateway to my MCP server" - "Protect my AI model with a gateway" - "Secure my AI agents" - "Ratelimit my model requests" - "Ratelimit my tool requests" - "Limit tokens for my model" - "Add rate limiting to my MCP server" - "Enable semantic caching for my AI API" - "Add content safety to my AI endpoint" - "Add my model behind gateway" - "Import API from OpenAPI spec" - "Add API to gateway from swagger" - "Convert my API to MCP" - "Expose my API as MCP server" **Key Indicators:** - User deploying Azure OpenAI, AI Foundry, or other AI models - User creating or managing MCP servers - User needs token limits, rate limiting, or quota management - User wants to cache AI responses to reduce costs - User needs content filtering or safety controls - User wants load balancing across multiple AI backends **Secondary Triggers (Proact
- Skill Activation Triggers
- Overview
- Key Resources
- Configuration Rules
- Pattern 1: Quick Bootstrap AI Gateway
- Bicep Template
- Pattern 2: Semantic Caching
- Pattern 3: Token Rate Limiting
- Pattern 4: Content Safety
- Pattern 5: Rate Limits for MCPs/OpenAPI Tools
- Pattern 6: Managed Identity Authentication
- Pattern 7: Load Balancing with Retry
- Pattern 8: Add AI Foundry Model Behind Gateway
- Step 1: Discover AI Foundry Projects and Available Models
Create resource group
az group create --name rg-aigateway --location eastus2
Deploy APIM with Bicep
az deployment group create \
Set environment variables
List AI Foundry resources (AI Services accounts)
az cognitiveservices account list --query "[?kind=='AIServices'].{name:name, resourceGroup:resourceGroup, location:location}" -o table
List available models in the AI Foundry resource
az cognitiveservices account list-models \
List already deployed modelsWhat does the azure-aigateway skill do?
Configure Azure API Management (APIM) as AI Gateway to secure, observe, control AI models, MCP servers, agents. Helps with rate limiting, semantic caching, content safety, load balancing. USE FOR: AI Gateway, APIM, setup gateway, configure gateway, add gateway, model gateway, MCP server, rate limit, token limit, semantic cache, content safety, load balance, OpenAPI import, convert API to MCP. DO NOT USE FOR: deploy models (use microsoft-foundry), Azure Functions (use azure-functions), databases (use azure-postgres).
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill azure-aigateway --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.