AI-Gateway
Labs to explore AI Models, MCP servers, and Agents with the AI Gateway powered by Azure API Management and Microsoft Foundry 🚀
AI-Gateway is a comprehensive learning resource and implementation guide for building enterprise-grade AI infrastructure using Azure API Management and Microsoft Foundry, including MCP server integration. It provides over 30 hands-on Jupyter notebook labs covering model management, MCP protocol implementation, and agentic workflows. Developers use these labs to deploy production-ready AI gateways with security policies, load balancing, semantic caching, and cost controls. The repository includes ready-to-deploy Bicep templates, APIM policy configurations, and tools for testing MCP servers with OAuth authentication and function calling.
Key Features
Use Cases
- 01Implementing secure MCP servers with enterprise OAuth authentication for AI tools
- 02Building multi-model AI gateways with automatic failover and load balancing
- 03Deploying semantic caching layers to reduce AI inference costs and latency
- 04Managing token consumption and budgets across multiple AI models and teams
- 05Creating agentic applications with MCP tool integration and function calling
- 06Testing and validating MCP server implementations with mock endpoints and tracing
Related MCP Servers
View moremarkitdown
Python tool for converting files and office documents to Markdown.
firecrawl
The context API to search, scrape, and interact with the web at scale. 🔥
prompts.chat
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
langflow
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
AI-Gateway — FAQ
What is AI-Gateway and what does it do?+
AI-Gateway is a lab-based learning repository for building enterprise AI infrastructure using Azure API Management. It includes hands-on tutorials for implementing MCP servers, managing AI models, and deploying agentic applications with security, observability, and cost controls.
How do I install and run the AI-Gateway labs?+
Clone the repository, install Python 3.12+ and uv package manager, run 'uv sync' to create the virtual environment, then open the Jupyter notebooks in VS Code. Each lab includes deployment steps for Azure resources using the provided Bicep templates.
What are the prerequisites for using AI-Gateway?+
You need an Azure subscription with Contributor and RBAC Administrator roles, Azure CLI authenticated to your subscription, Python 3.12+, uv package manager, and VS Code with the Jupyter extension. Some labs require specific API keys for OpenAI or other AI services.
Which AI clients work with the MCP servers built using these labs?+
The labs demonstrate MCP server integration with OpenAI Agents SDK, Google Gemini models, Azure AI Foundry, and realtime audio APIs. The MCP protocol implementation follows standard specifications compatible with MCP-enabled clients.
Is AI-Gateway free to use?+
The repository and code are open source under MIT license and free to use. However, deploying the labs to Azure will incur costs for Azure API Management, Azure OpenAI, and other Azure services used in the infrastructure.
Can I build custom MCP servers using this repository?+
Yes, the repository includes an 'mcp-builder' Copilot skill and comprehensive labs on MCP protocol implementation. You can use these as templates to create custom MCP servers with OAuth authentication, function calling, and tool integration.
How do I install AI-Gateway?+
Open the source repository on GitHub and follow its README. AI-Gateway is a mcp server — MCP Agents Market links you directly to the official repo.
Is AI-Gateway free?+
AI-Gateway is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.