AI-Gateway
Verified Safeby Azure-Samples
Overview
The project serves as a collection of labs demonstrating AI Gateway capabilities with Azure API Management, focusing on Model Context Protocol (MCP) to enable plug-and-play tool integration for Large Language Models (LLMs).
Installation
uvicorn shared/mcp-servers/spotify/http/mcp_server.py:app --host 0.0.0.0 --port 8080Environment Variables
- APIM_GATEWAY_URL
- SUBSCRIPTION_ID
- RESOURCE_GROUP_NAME
- APIM_SERVICE_NAME
- AZURE_TENANT_ID
- AZURE_CLIENT_ID
- POST_LOGIN_REDIRECT_URL
- APIM_IDENTITY_OBJECT_ID
- AZURE_MANAGED_IDENTITY_CLIENT_ID
Security Notes
The project extensively uses Azure's built-in security features like Managed Identity and OAuth 2.0 through Azure API Management's credential manager, which is a strong foundation. Secrets are generally managed via environment variables. The use of `subprocess.run` for Azure CLI commands is present but within expected boundaries for an Azure-focused lab. MCP servers bind to `0.0.0.0` by default, which is common for development but requires external network security in production. The complexity of OAuth flows, even with Azure's abstractions, always poses a risk of misconfiguration if not handled meticulously. No explicit 'eval' or obfuscation found.
Similar Servers
klavis
Develop and deploy AI agents that interact with a wide array of web services (e.g., Gmail, YouTube, LinkedIn, Supabase, Salesforce, Kubernetes) through a standardized Model Context Protocol (MCP), often orchestrated by an intelligent routing layer like Strata.
mcpo
Exposes Model Context Protocol (MCP) tools as OpenAPI-compatible HTTP servers.
mcp-openapi-server
A Model Context Protocol (MCP) server that exposes OpenAPI endpoints as MCP tools, along with optional support for MCP prompts and resources, enabling Large Language Models to interact with REST APIs.
agentor
Build and deploy scalable AI agents that can interact with various tools and communicate via A2A and MCP protocols.