Swagger Auto-Generation on MCP Server
Would you like to generate a swagger.json directly on an MCP server on-the-fly? In many use cases, using remote MCP servers is not uncommon. In particular, if you're using Azure API Management (APIM), Azure API Center (APIC) or Copilot Studio in Power Platform, integrating with remote MCP servers is inevitable.
CampusSphere: Building the Future of Campus AI with Microsoft's Agentic Framework
Project Overview We are a team of Imperial College Students committed to improving campus life through innovative multi-agent solutions. CampusSphere leverages Microsoft Azure AI capabilities to automate core university campus services. We created an end-to-end solution that allows both students and staff to access a multi-agent framework for room/gym booking, attendance tracking, calendar management, IoT monitoring and more. đ Our Initial Vision: Reimagining Campus Technology When our team at Imperial College London embarked on the CampusSphere project as part of Microsoft's Agentic Campus initiative, we had one clear ambition: to create an intelligent campus ecosystem that would fundamentally change how students, faculty, and staff interact with university services. The inspiration came from a simple observationâdespite living in an age of advanced AI, campus technology remained frustratingly fragmented. Students juggled multiple portals for course registration, room booking, dining services, and academic support. Faculty members navigated separate systems for teaching, research, and administrative tasks. The result? Countless hours wasted on mundane navigation tasks that could be better spent on learning, teaching, and innovation. Our vision was ambitious: create a single, intelligent interface that could understand natural language, anticipate user needs, and seamlessly integrate with existing campus infrastructure. We didn't just want to build another campus appâwe wanted to demonstrate how Microsoft's agentic AI technologies could create a truly intelligent campus companion. đ§ Enter CampusSphere CampusSphere is an intelligent campus assistant made up of multiple AI agents, each with a specific domain of expertise â all communicating seamlessly through a centralized architecture. Think of it as a digital concierge for campus life, where your calendar, attendance, IoT data, and facility bookings are coordinated by specialized GPT-powered agents. Hereâs what we built: TriageAgent â the brain of the system, using Retrieval-Augmented Generation (RAG) to understand user intent CalendarAgent â handles scheduling, bookings, and reminders AttendanceAgent â tracks check-ins automatically IoTAgent â monitors real-time sensor data from classrooms and labs GymAgent â manages access and reservations for sports facilities 30+ MCP Tools â perform SQL queries, scrape web data, and connect with external APIs All of this is built on Microsoft Azure AI, Semantic Kernel, and Model Context Protocol (MCP) â making it scalable, secure, and lightning fast. đ„ïž The Tech Stack Our Azure-powered architecture showcases a modular and scalable approach to real-time data processing and intelligent agent coordination. The frontend is built using React with a Vite development server, providing a fast and responsive user interface. When users submit a prompt, it travels to a Flask backend server acting as the Triage agent, which intelligently delegates tasks to a FastAPI agent service. This FastAPI service asynchronously communicates with individual agents and handles responses efficiently. Complex queries are routed to MCP Tools, which interact with the CosmosDB-powered Campus Database. Simultaneously, real-time synthetic IoT data is pushed into the database via Azure Function Apps and Azure IoT Hub. Authentication is securely managed: users log in through the frontend, receive a token from the database API server, and use it for authorized access to MCP services, with permissions enforced based on user roles using our custom MCP server implementation. This robust architecture enables seamless integration, real-time data flow, and secure multi-agent collaboration across Azure services. Our system leverages a multi-agent architecture designed to intelligently coordinate task execution across specialized services. At the core is the TriageAgent, which uses Retrieval-Augmented Generation (RAG) to interpret user prompts, enrich them with relevant context, and determine the optimal response path. Based on the nature of the request, it may handle the response directly, seek clarification, or delegate tasks to specific agents via FastAPI. Each specialized agent has a clearly defined role: AttendanceAgent: Interfaces with CosmosDB-backed FastAPI endpoints to check student attendance, using filters like event name, student ID, or date. IoTAgent: Monitors room conditions (e.g., temperature, COâ levels) and flags anomalies using real-time data from Azure IoT Hub, processed via FastAPI. CalendarAgent: Handles scheduling, availability checks, and event creation by querying or updating CosmosDB through FastAPI. Future integration with Microsoft Graph API is planned for direct calendar syncing. Gym Slot Agent: Checks available times for gym sessions using dedicated MCP tools. The triage agent serves as the orchestrator, breaking down complex requests (like "Book a gym session") into subtasks. It consults relevant agents (e.g., calendar and gym slot agents), merges results, and then confirms the final action with the user. This distributed and asynchronous workflow reduces backend load and enhances both responsiveness and reliability of the system. đź Whatâs Next? Integrating CampusSphere with live systems via Microsoft OAuth is crucial for enhancing its capabilities. This integration will grant the agent authenticated access to a wider range of student data, moving beyond synthetic datasets. This expanded access to real-world information will enable deeply personalized advice, such as tailored course selection, scholarship recommendations, event suggestions, and deadline reminders, transforming CampusSphere into a sophisticated, proactive personal assistant. đ€Meet the Team Behind CampusSphere Our success stemmed from a diverse team of innovators who brought together expertise from multiple domains: Benny Liu - https://www.linkedin.com/in/zong-benny-liu-393a4621b/ Lucas Ng - https://www.linkedin.com/in/lucas-ng-11b317203/ Lu Ju - https://www.linkedin.com/in/lu-ju/ Bruno Duaso - https://www.linkedin.com/in/bruno-duaso-jimeno-744464262/ Martim Coutinho - https://www.linkedin.com/in/martim-pereira-coutinho-116308233/ Krischad Pourpongpan - https://www.linkedin.com/in/krischadpua/ Yixu Pan - https://www.linkedin.com/in/yixu-pan/ Our collaborative approach enabled us to create a sophisticated agentic AI system that demonstrates the powerful potential of Microsoft's AI technologies in educational environments. đ§âđ» Project Repository: GitHub - Imperial-Microsoft-Agentic-Campus/CampusSphere Contribute to Imperial-Microsoft-Agentic-Campus/CampusSphere development by creating an account on GitHub. github.com Have questions about implementing similar solutions at your institution? Connect with our team members on LinkedInâwe're always excited to share knowledge and collaborate on innovative campus technology projects. đGet Started with Microsoft's AI Tools Ready to explore the technologies that made CampusSphere possible? Here are essential resources: Microsoft Semantic Kernel: The core framework for building AI agent orchestration systems. Learn how to create, coordinate, and manage multiple AI agents working together seamlessly. AI Agents for Beginners: A comprehensive guide to understanding and building AI agents from the ground up. Perfect for getting started with agentic AI development. Model Context Protocol (MCP): Learn about the protocol that enables secure connections between AI models and external tools and servicesâessential for building integrated AI systems. Windows AI Toolkit: Microsoft's toolkit for developing AI applications on Windows, providing local AI model development capabilities and deployment tools. Azure Container Apps: Understand how to deploy and scale containerized AI applications in the cloud, perfect for hosting multi-agent systems. Azure Cosmos DB Security: Essential security practices for managing data in AI applications, covering encryption, access control, and compliance.Impariamo a conoscere MCP: Introduzione al Model Context Protocol (MCP)
Non perderti il prossimo evento âLetâs Learn â MCPâ su Microsoft Reactor il 24 di Luglio, pensato per chiunque voglia conoscere meglio il nuovo standard per agenti intelligenti (il Model Context Protocol) e imparare a metterlo in pratica. La sessione Ăš in Italiano e le demo sono in Python, ma fa parte di una serie di live-streaming disponibili in tantissime lingue.How do I get my agent to respond in a structured format like JSON?
Welcome back to Agent Supportâa developer advice column for those head-scratching moments when youâre building an AI agent! Each post answers a real question from the community with simple, practical guidance to help you build smarter agents. đŹ Dear Agent Support Iâm building an agent that feeds its response into another appâbut sometimes the output is messy or unpredictable. Can you help? This looks like a job for JSON! While agent output often comes back as plain text, there are times when you need something more structured, especially if another system, app, or service needs to reliably parse and use that response. đ§ Whatâs the Deal with JSON Output? If your agent is handing off data to another app, you need the output to be clean, consistent, and easy to parse. Thatâs where JSON comes in. JSON (JavaScript Object Notation) is a lightweight, widely supported format that plays nicely with almost every modern tool or platform. Whether your agent is powering a dashboard, triggering a workflow, or sending data into a UI component, JSON makes the handoff smooth. You can define exactly what shape the response should take (i.e. keys, values, types) so that other parts of your system know what to expect every single time. Without it? Things get messy fast! Unstructured text can vary wildly from one response to the next. A missing field, a misaligned format, or even just an unexpected line break can break downstream logic, crash a frontend, or silently cause bugs you wonât catch until much later. Worse, you end up writing brittle post-processing code to clean up the output just to make it usable. The bottom line: If you want your agent to work well with others, it needs to speak in a structured format. JSON isnât just a nice-to-have, itâs the language of interoperability. 𧩠When Youâd Want Structured Output Not every agent needs to speak JSON, but if your response is going anywhere beyond the chat window, structured output is your best bet. Letâs say your agent powers a dashboard. You might want to display the response in different UI componentsâa title, a summary, maybe a set of bullet points. That only works if the response is broken into predictable parts. Same goes for workflows. If youâre passing the output into another service, like Power Automate, an agent framework like Semantic Kernal, or even another agent, it needs to follow a format those systems can recognize. Structured output also makes logging and debugging easier. When every response follows the same format, you can spot problems faster. Missing fields, weird values, or unexpected data types stand out immediately. It also future proofs your agent. If you want to add new features later, like saving responses to a database or triggering different actions based on the content, having structured output gives you the flexibility to build on top of whatâs already there. If the output is meant to do more than just be read by a human, it should be structured for a machine. đ How to Define a JSON Format Once you know your agentâs output needs to be structured, the next step is telling the model exactly how to structure it. Thatâs where defining a schema comes in. In this context, a schema is just a blueprint for the shape of your data. It outlines what fields you expect, what type of data each one should hold, and how everything should be organized. Think of it like a form template: the model just needs to fill in the blanks. Hereâs a simple example of a JSON schema for a to-do app: { "task": "string", "priority": "high | medium | low", "due_date": "YYYY-MM-DD" } Once you have your format in mind, include it directly in your prompt. But if youâre using the AI Toolkit in Visual Studio Code, you donât have to do this manually every time! đ§ Create a JSON schema with the AI Toolkit The Agent Builder feature supports structured output natively. You can provide a JSON schema alongside your prompt, and the agent will automatically aim to match that format. This takes the guesswork out of prompting. Instead of relying on natural language instructions to shape the output, youâre giving the model a concrete set of instructions to follow. Hereâs how to do it: Open the Agent Builder from the AI Toolkit panel in Visual Studio Code. Click the + New Agent button and provide a name for your agent. Select a Model for your agent. Within the System Prompt section, enter: You recommend a movie to watch. Within the User Prompt section, enter: Recommend a science-fiction movie with robots. In the Structured Output section, select json_schema as the output format. Click Prepare schema. In the wizard, select Use an example. For the example, select paper_metadata. Save the file to your desired location. You can name the file: movie_metadata. In the Agent Builder, select movie_metadata to open the file. Using the template provided, modify the schema to format the title, genre, year, and reason. Once done, save the file. { "name": "movie_metadata", "strict": true, "schema": { "type": "object", "properties": { "title": { "type": "string" }, "genre": { "type": "array", "items": { "type": "string" } }, "year": { "type": "string" }, "reason": { "type": "array", "items": { "type": "string" } } }, "required": [ "title", "genre", "year", "reason" ], "additionalProperties": false } } And just like that, youâve set up a JSON schema for your agentâs output! đ§Ș Test Before You Build You can submit a prompt with the Agent Builder to validate whether the agent adheres to the JSON schema when returning its response. When you click Run, the agentâs response will appear in the Prompt tab, ideally in JSON format. đ Recap Hereâs a quick rundown of what we covered: JSON lets you create reliable, machine-friendly agent responses. JSON is essential for interoperability between apps, tools, and workflows. Without JSON, you risk fragile pipelines, broken features, or confusing bugs. The AI Toolkit supports including a JSON schema with your agentâs prompt. đș Want to Go Deeper? Check out the AI Agents for Beginners curriculum in which we dive a bit more into agentic design patterns which includes defining structured outputs. Weâll have a video landing soon in the Build an Agent Series that takes you through a step-by-step look of creating a JSON schema for your agent!Learn Together: Building an MCP Server with AI Toolkit
AI is evolving fastâbut building real, useful AI applications still requires more than just a smart model. Thatâs where the Model Context Protocol (MCP) comes in. MCP is an open standard that helps AI systems talk to tools, data, and services in a clean, reusable way. Think of it as the coordination layer that turns a smart model into an intelligent application. Whether youâre integrating APIs, calling scripts, or orchestrating multiple agents, MCP provides the structure that makes it all work together. And thanks to the AI Toolkit for Visual Studio Code, working with MCP is now easier than ever. The toolkit gives you an intuitive playground, built-in server tools, model integration, and everything you need to go from idea to working prototype without leaving your editor. đ Join the Event: Learn Together â Building an MCP Server with AI Toolkit In this live, hands-on workshop, weâll walk through four practical modules designed to help you build, configure, and test your own MCP server from scratch. Youâll get to follow along step-by-step using the AI Toolkit extension for VS Code. Whether you're building multi-agent workflows, enabling tools in a RAG app, or just looking for a smarter way to connect your models to real-world actions, this workshop is for you. đ§Ș What Youâll Learn â Inside the Labs Hereâs a preview of the four modules weâll cover during the livestream: Module 1: Getting Started with AI Toolkit In this lab, youâll install and configure the AI Toolkit for Visual Studio Code, then dive into its key featuresâlike the model catalog, interactive playground, and agent builder. You'll build your first functional agent, experiment with real-time model testing, and evaluate outputs using built-in metrics. Along the way, youâll also explore batch processing and multimodal support. By the end, youâll have a solid foundation in what the AI Toolkit can do. Module 2: Integrating MCP with Your Agents This lab introduces the Model Context Protocol (MCP) and shows you how to supercharge your AI agents with tool-using capabilities. Youâll connect to existing MCP servers, like the Playwright automation server, then integrate them into your agents using the AI Toolkit. From configuring tools to testing and deploying MCP-powered agents, youâll see how external tools become part of your modelâs workflow. This lab is your bridge between smart models and real-world actions. Module 3: Building and Debugging Custom MCP Servers Here, youâll go beyond using prebuilt MCP servers and start creating your own. Youâll learn how to use the latest MCP Python SDK to configure and debug a custom server, including a weather tool example. The lab walks through setting up the MCP Inspector, testing tool calls, and running agents in a local dev environment. Youâll leave with a full understanding of how to build, test, and debug your own MCP endpoints. Module 4: Real-World MCP Server â GitHub Clone Agent In this final lab, youâll build a GitHub clone MCP server that replicates real dev workflows. It features smart repo cloning, intelligent directory setup, error handling, and direct integration with VS Code. Youâll even enable GitHub Copilotâs Agent Mode to interact with your custom tools. This lab wraps everything together into a production-grade example of whatâs possible with MCP. đĄ Why MCP + AI Toolkit? The magic of MCP is in its modularity. It gives developers a structured way to define tools, link models, and control interactions, all in a language-agnostic, reusable way. And when paired with the AI Toolkit, you get a guided development experience with built-in tools for testing, telemetry, evaluation, and more. Whether you're building an agent to automate tasks, assist users, or connect enterprise systems, MCP makes it possible. The AI Toolkit makes it easier! đ Save the Date! Donât miss your chance to build alongside us and see MCP in action. This is more than just a demo, itâs a full walkthrough of what modern, production-aware AI development looks like. â Register now to join the Learn Together livestream on the 5th August and take your first step toward building smarter AI applications. đ Click here to register for the event!JS AI Build-a-thon: Project Showcase
In the JS AI Build-a-thon, quest 9 was all about shipping faster, smarter, and more confidently. This quest challenged developers to skip the boilerplate and focus on what really matters, solving real-world problems with production-ready AI templates and cloud-native tools. And wow, did our builders deliver, with a massive 28 projects. From personalized chatbots to full-stack RAG applications, participants used the power of the Azure Developer CLI (azd) and robust templates to turn ideas into fully deployed AI solutions on Azure, in record time. What This Quest Was About Quest 9 focused on empowering developers to: Build AI apps faster with production-ready templates Use Azure Developer CLI (azd) to deploy with just a few commands Leverage Infrastructure-as-Code (IaC) to provision everything from databases to APIs Follow best practices out of the box â scalable, secure, and maintainable Participants explored a curated gallery of templates and learned how to adapt them to their unique use cases. No Azure experience? No problem. azd made setup, deployment, and teardown as simple as azd up. đ„And the winner is..... With the massive votes from the community, the winning project as AI Academic advisor by Aryanjstar AI Career Navigator - Your Personal AI Career Coach by Aryanjstar [Project Submission] AI Career Navigator - Your Personal AI Career Coach · Issue #47 · Azure-Samples/JS-AI-Build-a-thon Aryan, a Troop Leader of the Geo Cyber Study Jam, created the AI Career Navigator to address common challenges faced by developers in the tech job market, such as unclear skill paths, resume uncertainty, and interview anxiety. Built using the Azure Search OpenAI Demo template, the tool offers features like resume-job description matching, skill gap analysis, and dynamic interview preparation. The project leverages a robust RAG setup and Azure integration to deliver a scalable, AI-powered solution for career planning. đ„ Other featured projects: Deepmine-sentinel by Josephat-Onkoba [Project Submission] Deepmine-Sentinel · Issue #29 · Azure-Samples/JS-AI-Build-a-thon DeepMine Sentinel AI is an intelligent safety assistant designed to tackle the urgent risks facing workers in the mining industry, one of the most hazardous sectors globally. Built by customizing the âGet Started with Chatâ Azure template, this solution offers real-time safety guidance and monitoring to prevent life-threatening incidents like cave-ins, toxic gas exposure, and equipment accidents. In regions where access to safety expertise is limited, DeepMine Sentinel bridges the gap by delivering instant, AI-powered support underground, ensuring workers can access critical information and protocols when they need it most. With a focus on accessibility, real-world impact, and life-saving potential, this project demonstrates how AI can be a powerful force for good in high-risk environments. PetPal - Your AI Pet Care Assistant by kelcho-spense [Project Submission] PetPal - Your AI Pet Care Assistant · Issue #70 · Azure-Samples/JS-AI-Build-a-thon PetPal is an AI-powered pet care assistant designed to support pet owners, especially first-timers, by offering instant, reliable answers to common pet-related concerns. From health and nutrition advice to emergency support and behavioral training, PetPal uses a serverless architecture powered by LangChain.js, Azure OpenAI, and Retrieval-Augmented Generation (RAG) to deliver accurate, context-aware responses. The app features a warm, pet-themed interface built with Lit and TypeScript, and includes thoughtful customizations like pet profile management, personalized chat history, and species-specific guidance. With backend services hosted on Azure Functions and data stored in Azure Cosmos DB, PetPal is production-ready, scalable, and focused on reducing anxiety while promoting responsible and informed pet ownership. MLSA LearnBot by Shunlexxi [Project Submission] MLSA LearnBot · Issue #67 · Azure-Samples/JS-AI-Build-a-thon Navigating the Microsoft Learn Student Ambassadors program can be overwhelming. To solve this, a student built an Intelligent Chatbot Q&A App using a Microsoft azd template, transforming a generic AI chatbot into a tailored assistant for Student Ambassadors and aspiring members. By integrating essential documentation, FAQs, and natural language support with Azure services like App Service, AI Search, and OpenAI, this tool empowers students to get instant, reliable answers and navigate their roles with ease. The front end was customized to reflect a student-friendly brand, and deployment was simplified using azd for a seamless, production-ready experience. You okay? Meet Vish AI, your mental health companion by ToshikSoni [Project Submission] You okay? Meet Vish AI, your mental health companion · Issue #38 · Azure-Samples/JS-AI-Build-a-thon Vish.AI is an empathetic GenAI companion designed to support emotional well-being, especially for individuals facing depression, loneliness, and mental burnout. Built using Azureâs AI Chat RAG template and enhanced with LangChain for conversational memory, the assistant offers a deeply personalized experience that remembers past interactions and responds with both emotional intelligence and informed support. By integrating a curated collection of resources on mental health into its RAG system, Vish.AI provides meaningful guidance and a comforting presence, available anytime, anywhere. Created to bridge the gap for those who may not feel comfortable opening up to friends or family, this project combines AI with a human touch to offer always-accessible care, demonstrating how thoughtful technology can help make life a little lighter for those quietly struggling. Want to Catch Up? If you missed the Build-a-thon or want to explore other quests (there are 9!), check them out here: đ GitHub - Azure-Samples/JS-AI-Build-a-thon If you want to catch up with how the challenge went and how you can get started, check out đJS AI Buildâaâthon: Wrapping Up an Epic June 2025! | Microsoft Community Hub Join the Community The conversation isnât over. The Quests are now self-paced. Weâre keeping the momentum going over on Discord in the #js-ai-build-a-thon channel. Drop your questions, showcase your builds, or just come hang out with other builders. đ Join the community on Join the Azure AI Foundry Discord Server! Additional Resources đ Microsoft for JavaScript developers đ Generative AI for Beginners with JavaScriptAI Toolkit for VS Code July Update
Weâre back with the July update for the AI Toolkit for Visual Studio Code! This month marks a major releaseâversion 0.16.0âbringing features we teased in the June prerelease into full availability, along with new enhancements across the board. đł GitHub Pay-as-you-go Model Support AI Toolkit now supports GitHub pay-as-you-go models, making it easier to continue building without friction when you exceed the free tier limits. Hereâs how it works: When you hit the usage limit for GitHubâs hosted models, AI Toolkit will provide a clear prompt with a link to GitHubâs paid usage documentation. You can enable model usage billing in your GitHub Settings. Once enabled, you can continue using the same model in the Playground or Agent Builderâno changes needed in your workflow. This integration helps keep your development flow uninterrupted while giving you flexibility on how and when to scale. đ€ Agent Builder Enhancements In last monthâs June update, we introduced early access to function calling and agent version managementâtwo highly requested features for building more reliable and dynamic AI agents. With v0.16.0, these features are now officially included in the stable release. Weâve also made several usability improvements: Resizable divider between input and output panels Cleaner, more compact evaluation results table Explore the latest features in the Agent Builder documentation. đ Agent Development in VS Code: From Local to Cloud Whether youâre just getting started or ready to scale, AI Toolkit now makes it seamless to go from local experiments to production-ready deployments in the cloud. đ Discover and Deploy Models with Ease You can now browse and explore a growing collection of modelsâincluding 100+ models from Azure AI Foundryâdirectly in the Model Catalog view. Once youâve selected a model, you can deploy it to Azure AI Foundry with a single click, all within VS Code. âĄïž Learn more about the Model Catalog âĄïž How deployment works in Azure AI Foundry âïž Iterate Locally, Scale When Ready The Playground and Agent Builder experience is designed to help you with prototyping quickly. Start with free, hosted models on GitHub to experiment with prompts and agent behavior. As your use case grows, you might hit rate limits or token capsâwhen that happens, the toolkit will proactively guide you to deploy the same model to Azure AI Foundry, so you can continue testing without interruption. đ Get Started and Share Your Feedback If you havenât tried the AI Toolkit for VS Code yet, now is a great time to get started. Install it directly from the Visual Studio Code Marketplace and begin building intelligent agents today. Weâd love to hear from you! Whether it's a feature request, a bug report, or feedback on your experience, join the conversation and contribute directly on our GitHub repository. Letâs build the future of AI agent development together đĄđŹ đ See full changelog for v0.16.0 đ§ AI Toolkit Documentation Happy coding, and see you in August!Multi-Agent Systems and MCP Tools Integration with Azure AI Foundry
The Power of Connected Agents: Building Multi-Agent Systems Imagine trying to build an AI system that can handle complex workflows like managing support tickets, analyzing data from multiple sources, or providing comprehensive recommendations. Sounds challenging, right? That's where multi-agent systems come in! The Develop a multi-agent solution with Azure AI Foundry Agent Services module introduces you to the concept of connected agents a game changing approach that allows you to break down complex tasks into specialized roles handled by different AI agents. Why Connected Agents Matter As a student developer, you might wonder why you'd need multiple agents when a single agent can handle many tasks. Here's why this approach is transformative: 1. Simplified Complexity: Instead of building one massive agent that does everything (and becomes difficult to maintain), you can create smaller, specialized agents with clearly defined responsibilities. 2. No Custom Orchestration Required: The main agent naturally delegates tasks using natural language - no need to write complex routing logic or orchestration code. 3. Better Reliability and Debugging: When something goes wrong, it's much easier to identify which specific agent is causing issues rather than debugging a monolithic system. 4. Flexibility and Extensibility: Need to add a new capability? Just create a new connected agent without modifying your main agent or other parts of the system. How Multi-Agent Systems Work The architecture is surprisingly straightforward: 1. A main agent acts as the orchestrator, interpreting user requests and delegating tasks 2. Connected sub-agents perform specialized functions like data retrieval, analysis, or summarization 3. Results flow back to the main agent, which compiles the final response For example, imagine building a ticket triage system. When a new support ticket arrives, your main agent might: - Delegate to a classifier agent to determine the ticket type - Send the ticket to a priority-setting agent to determine urgency - Use a team-assignment agent to route it to the right department All this happens seamlessly without you having to write custom routing logic! Setting Up a Multi-Agent Solution The module walks you through the entire process: 1. Initializing the agents client 2. Creating connected agents with specialized roles 3. Registering them as tools for the main agent 4. Building the main agent that orchestrates the workflow 5. Running the complete system Taking It Further: Integrating MCP Tools with Azure AI Agents Once you've mastered multi-agent systems, the next level is connecting your agents to external tools and services. The Integrate MCP Tools with Azure AI Agents module teaches you how to use the Model Context Protocol (MCP) to give your agents access to a dynamic catalog of tools. What is Dynamic Tool Discovery? Traditionally, adding new tools to an AI agent meant hardcoding each one directly into your agent's code. But what if tools change frequently, or if different teams manage different tools? This approach quickly becomes unmanageable. Dynamic tool discovery through MCP solves this problem by: 1. Centralizing Tool Management: Tools are defined and managed in a central MCP server 2. Enabling Runtime Discovery: Agents discover available tools during runtime through the MCP client 3. Supporting Automatic Updates: When tools are updated on the server, agents automatically get the latest versions The MCP Server-Client Architecture The architecture involves two key components: 1. MCP Server: Acts as a registry for tools, hosting tool definitions decorated with `@mcp.tool`. Tools are exposed over HTTP when requested. 2. MCP Client: Acts as a bridge between your MCP server and Azure AI Agent. It discovers available tools, generates Python function stubs to wrap them, and registers those functions with your agent. This separation of concerns makes your AI solution more maintainable and adaptable to change. Setting Up MCP Integration The module guides you through the complete process: 1. Setting up an MCP server with tool definitions 2. Creating an MCP client to connect to the server 3. Dynamically discovering available tools 4. Wrapping tools in async functions for agent use 5. Registering the tools with your Azure AI agent Once set up, your agent can use any tool in the MCP catalog as if it were a native function, without any hardcoding required! Practical Applications for Student Developers As a student developer, how might you apply these concepts in real projects? Classroom Projects: - Build a research assistant that delegates to specialized agents for different academic subjects - Create a coding tutor that uses different agents for explaining concepts, debugging code, and suggesting improvements Hackathons: - Develop a sustainability app that uses connected agents to analyze environmental data from different sources - Create a personal finance advisor with specialized agents for budgeting, investment analysis, and financial planning Personal Portfolio Projects: - Build a content creation assistant with specialized agents for brainstorming, drafting, editing, and SEO optimization - Develop a health and wellness app that uses MCP tools to connect to fitness APIs, nutrition databases, and sleep tracking services Getting Started Ready to dive in? Both modules include hands-on exercises where you'll build real working examples: - A ticket triage system using connected agents - An inventory management assistant that integrates with MCP tools The prerequisites are straightforward: - Experience with deploying generative AI models in Azure AI Foundry - Programming experience with Python or C# Conclusion Multi-agent systems and MCP tools integration represent the next evolution in AI application development. By mastering these concepts, you'll be able to build more sophisticated, maintainable, and extensible AI solutions - skills that will make you stand out in internship applications and job interviews. The best part? These modules are designed with practical, hands-on learning in mind - perfect for student developers who learn by doing. So why not give them a try? Your future AI applications (and your resume) will thank you for it! Want to learn more about Model Context Protocol 'MCP' see MCP for Beginners Happy coding!How do I give my agent access to tools?
Welcome back to Agent Supportâa developer advice column for those head-scratching moments when youâre building an AI agent! Each post answers a real question from the community with simple, practical guidance to help you build smarter agents. Todayâs question comes from someone trying to move beyond chat-only agents into more capable, action-driven ones: đŹ Dear Agent Support I want my agent to do more than just respond with text. Ideally, it could look up information, call APIs, or even run codeâbut Iâm not sure where to start. How do I give my agent access to tools? This is exactly where agents start to get interesting! Giving your agent tools is one of the most powerful ways to expand what it can do. But before we get into the âhow,â letâs talk about what tools actually mean in this contextâand how Model Context Protocol (MCP) helps you use them in a standardized, agent-friendly way. đ ïž What Do We Mean by âToolsâ? In agent terms, a tool is any external function or capability your agent can use to complete a task. That might be: A web search function A weather lookup API A calculator A database query A custom Python script When you give an agent tools, youâre giving it a way to take actionânot just generate text. Think of tools as buttons the agent can press to interact with the outside world. ⥠Why Give Your Agent Tools? Without tools, an agent is limited to what it âknowsâ from its training data and prompt. It can guess, summarize, and predict, but it canât do. Tools change that! With the right tools, your agent can: Pull live data from external systems Perform dynamic calculations Trigger workflows in real time Make decisions based on changing conditions Itâs the difference between an assistant that can answer trivia questions vs. one that can book your travel or manage your calendar. 𧩠So⊠How Does This Work? Enter Model Context Protocol (MCP). MCP is a simple, open protocol that helps agents use tools in a consistent wayâwhether those tools live in your app, your cloud project, or on a server you built yourself. Hereâs what MCP does: Describes tools in a standardized format that models can understand Wraps the function call + input + output into a predictable schema Lets agents request tools as needed (with reasoning behind their choices) This makes it much easier to plug tools into your agent workflow without reinventing the wheel every time! đ How to Connect an Agent to Tools Wiring tools into your agent might sound complex, but it doesnât have to be! If youâve already got a MCP server in mind, thereâs a straightforward way within the AI Toolkit to expose it as a tool your agent can use. Hereâs how to do it: Open the Agent Builder from the AI Toolkit panel in Visual Studio Code. Click the + New Agent button and provide a name for your agent. Select a Model for your agent. Within the Tools section, click + MCP Server. In the wizard that appears, click + Add Server. From there, you can select one of the MCP servers built my Microsoft, connect to an existing server thatâs running, or even create your own using a template! After giving the server a Server ID, youâll be given the option to select which tools from the server to add for your agent. Once connected, your agent can call tools dynamically based on the task at hand. đ§Ș Test Before You Build Once youâve connected your agent to an MCP server and added tools, donât jump straight into full integration. Itâs worth taking time to test whether the agent is calling the right tool for the job. You can do this directly in the Agent Builder: enter a test prompt that should trigger a tool in the User Prompt field, click Run, and observe how the model responds. This gives you a quick read on tool call accuracy. If the agent selects the wrong tool, itâs a sign that your system prompt might need tweaking before you move forward. However, if the agent calls the correct tool but the output still doesnât look right, take a step back and check both sides of the interaction. It might be that the system prompt isnât clearly guiding the agent on how to use or interpret the toolâs response. But it could also be an issue with the tool itselfâwhether thatâs a bug in the logic, unexpected behavior, or a mismatch between input and expected output. Testing both the tool and the prompt in isolation can help you pinpoint where things are going wrong before you move on to full integration. đ Recap Hereâs a quick rundown of what we covered: Tools = external functions your agent can use to take action MCP = a protocol that helps your agent discover and use those tools reliably If the agent calls the wrong toolâor uses the right tool incorrectlyâcheck your system prompt and test the tool logic separately to isolate the issue. đș Want to Go Deeper? Check out my latest video on how to connect your agent to a MCP serverâitâs part of the Build an Agent Series, where I walk through the building blocks of turning an idea into a working AI agent. The MCP for Beginners curriculum covers all the essentialsâMCP architecture, creating and debugging servers, and best practices for developing, testing, and deploying MCP servers and features in production environments. It also includes several hands-on exercises across .NET, Java, TypeScript, JavaScript and Python. đ Explore the full curriculum: aka.ms/AITKmcp And for all your general AI and AI agent questions, join us in the Azure AI Foundry Discord! You can find me hanging out there answering your questions about the AI Toolkit. I'm looking forward to chatting with you there! Whether youâre building a productivity agent, a data assistant, or a game botâtools are how you turn your agent from smart to useful.
