Content by jordanselig (21)

jordanselig announces a public preview feature that lets Azure App Service expose an existing REST API as a Model Context Protocol (MCP) server using only an OpenAPI spec. The post covers how the platform generates MCP tools, how to configure it, and what to consider for authentication and safe exposure.

jordanselig shares a runnable reference architecture for putting Azure API Management in front of Azure OpenAI, with an App Service-hosted agent and a co-located MCP server. The focus is on governance via APIM policies (semantic cache, token limits, metrics/chargeback) while keeping the agent framework interchangeable.

jordanselig walks through a practical debugging workflow for Python FastAPI apps running on Azure App Service for Linux, using new built-in SSH helper aliases to quickly diagnose common production failures like bad endpoints, DNS issues, managed identity auth problems, missing dependencies, port mismatches, and latency spikes.

jordanselig shares a production-minded LLMOps reference sample for running a self-healing agent on Azure App Service, covering agent-specific SLIs, OpenTelemetry metrics into Application Insights, cost circuit breakers with model downshifting, prompt-repair retries, chaos testing, and an automated slot-swap rollback driven by alerts and a Logic App.

jordanselig shows how to run a stateless Model Context Protocol (MCP) server on Azure App Service so it can sit behind the platform load balancer and scale out cleanly. The post includes a runnable FastAPI sample, Bicep infrastructure, Application Insights verification queries, and a k6 load test to confirm traffic distribution across instances.

jordanselig shows how to add runtime governance to a multi-agent ASP.NET Core travel planner on Azure App Service using the Microsoft Agent Governance Toolkit, including YAML policy allowlists, audit logging into Application Insights, and SRE controls like SLOs and circuit breakers.

jordanselig shows how to instrument Microsoft Agent Framework agents with OpenTelemetry GenAI semantic conventions and send that telemetry to Azure Application Insights, enabling the Agents (Preview) view for per-agent token usage, latency, errors, and end-to-end agent runs across an ASP.NET Core API and a WebJob.

jordanselig walks through building an MCP App (a tool plus a UI resource) with ASP.NET Core, rendering an interactive weather widget inside chat clients like VS Code Copilot, and deploying the MCP server to Azure App Service using azd and Bicep.

jordanselig details a practical approach to running the open-source OpenClaw AI assistant 24/7 on Azure App Service. The guide covers architecture, deployment steps, security, persistent storage, cost factors, and how Azure OpenAI and managed identity streamline and secure the setup.

jordanselig demonstrates how the App Service Observability MCP Server has expanded from a local IDE tool to a scalable, AI-powered web solution on Azure App Service, leveraging Azure OpenAI and robust DevOps integration.

Jordan Selig demonstrates how developers can leverage an MCP server to connect GitHub Copilot with Azure App Service logs, enabling AI-driven diagnostics and troubleshooting directly in the IDE or CLI.

jordanselig describes how Easy MCP enables seamless integration of existing REST APIs with AI agents like GitHub Copilot on Azure App Service—with zero code changes required.

jordanselig walks through modern approaches for building AI agents and agentic web apps on Azure App Service, highlighting integration strategies, frameworks, and practical developer resources.

jordanselig explains how developers can build client-side multi-agent systems on Azure App Service using ChatClientAgent and the Microsoft Agent Framework, sharing architecture insights, code samples, and decision factors.

jordanselig demonstrates how to build sophisticated multi-agent AI solutions on Azure App Service using Microsoft Agent Framework, providing real-world workflow orchestration and deployment guidance for developers.

jordanselig delivers a comprehensive guide on developing robust, intelligent AI agents using Microsoft Agent Framework and Azure App Service, addressing long-running workflow scenarios with modern async architectures.

jordanselig explains how Outbound Network Segmentation for App Service Environment v3 (ASEv3) enables Azure app developers and admins to manage outbound traffic routing, providing improved security and compliance controls.

jordanselig illustrates how to build sophisticated multi-agent AI applications on Azure App Service, combining Azure AI Foundry, .NET Aspire, and MCP tooling for a cloud-native, scalable, and observable solution.

jordanselig details the new self-service quota management experience for Azure App Service, helping developers and IT admins proactively manage resource limits via an updated portal interface.

jordanselig walks through how developers can connect Azure AI Foundry agents to any application using the Model Context Protocol (MCP) and App Service, with practical examples and deployment guidance.

jordanselig from Microsoft announces the general availability of inbound IPv6 support for Azure App Service, outlining its implementation, configuration, and future plans.