Content by lily-ma (10)

lily-ma explains how to extend Azure SRE Agent with MCP servers by hosting them in Azure Connector Namespace, then wiring them into the agent’s connector experience. The post includes an end-to-end example using Azure Developer CLI (azd), managed identity auth, and access policies to connect a hosted SQL MCP server.

lily-ma explains how to handle long-running Model Context Protocol (MCP) tool calls on Azure Functions when clients time out, using Durable Functions as a practical pattern today and outlining how the MCP Tasks extension will eventually standardize async tool execution.

lily-ma summarizes what’s new in the Azure Functions MCP extension at Build 2026, covering the full MCP primitive set (tools, resources, prompts), MCP Apps for interactive UI, built-in MCP authentication with Entra ID, and .NET-focused improvements like fluent configuration APIs and explicit input/output schemas.

lily-ma introduces Hosted MCP Servers in Azure Logic Apps Connector Namespace (public preview), a managed way to deploy remote MCP endpoints from a catalog so AI agents can discover and call tools without you owning the underlying infrastructure, scaling, authentication, or monitoring setup.

lily-ma announces a public preview update to the Azure Functions MCP extension: a new MCP prompt trigger that completes support for MCP’s core server primitives (tools, resources, and prompts). The post explains what MCP prompts are, shows Python examples, and links to quickstarts and docs.

lily-ma explains how to connect an MCP server hosted on Azure Functions to an Azure AI Foundry agent, covering why you’d do it, the main authentication options (keys, Entra ID/managed identity, OAuth passthrough), and the high-level steps to register the MCP endpoint as a tool and test tool-calling in the agent playground.

lily-ma explains how to leverage the new MCP Apps support in Azure Functions MCP Extension to build interactive AI agent tools. The post covers fundamentals, example code, scenarios, and security practices.

Lily Ma presents a comprehensive developer guide for building and hosting ChatGPT apps on Azure Functions, covering architecture, integration, and deployment tips.

lily-ma presents a comprehensive overview of hosting remote Model Context Protocol (MCP) servers on Azure Functions, helping developers deploy secure, scalable agent tools using extension or SDK hosting options.

lily-ma presents the early preview of hosting bring-your-own Remote MCP servers on Azure Functions, making it easier for developers to deploy existing MCP SDK-based servers to a highly scalable serverless environment.