Enhance_GitHub_Copilot_using_MCP_-_Enterprise_version.pdf

Slide deck related to the GitHub Copilot Bootcamp in Melbourne on 17 June 2025. The presentation covered how remote MCP servers can be used with GitHub copilot. The servers were hosted in Azure API Management using the new GenAI capabilities

Transcript

1. Nilesh Gule @nileshgule Enhance GitHub Copilot using MCP Enterprise version
2. $whoami { “name” : “Nilesh Gule”, “website” : “https://www.HandsOnArchitect.com", “github” : “https://GitHub.com/NileshGule" “twitter” : “@nileshgule”, “linkedin” : “https://www.linkedin.com/in/nileshgule”, “YouTube” : “https://www.YouTube.com/@nilesh-gule” “likes” : “Technical Evangelism, Cricket”, }
3. MCP – newest kid in town MCP Host LLM application that needs access to external capabilities MCP Clients Protocol client that maintains 1:1 connection with servers inside host app MCP Servers Lightweight programs that each expose specific capabilities and provide context, tools and prompts to clients MCP Protocol Transport layer in the middle
4. Converging Agentic Extensibility with MCP Multi-Service Integration Agents or orchestrators can flexibly call a wide range of external APIs/tools Reusable Tools Once written the Tool can be used by any MCP-compatible client with minimal friction Enterprise Scalability Potential to unify multiple teams’ AI Integrations into a single product Ecosystem Momentum Anthropic, Perplexity, VS Code, Azure, Copilot Studio all support MCP; OpenAI & Google have announced plans GitHub star growth for MCP repo since launch (Dec 2024–Mar 2025). The project amassed over 15k stars within a few months, highlighting rapid developer traction​
5. Model Context Protocol at Microsoft Copilot Studio VS Code Foundry Agent Visual Studio GitHub Copilot Microsoft Teams Semantic Kernel MCP Clients & Host Tools Community Enterprise Windows Registry C# MCP SDK Azure API Management Azure Functions Microsoft Connectors Build Local & Remote MCPs MPC enables seamless Integration between LLM Apps and external data sources Model Context Protocol
6. AI Gateway capabilities of Azure API Management AI Gateway Security & safety • Keyless managed identities • AI Apps & Agents Authorizations -New • Content Safety -GA • Credential Manager Resiliency • Weight load balancing • Priority routing to provisioned capacity models • Backend pools with circuit breaker • Session aware load balancing -GA Scalability • Token rate limits and token quotas • Semantic Caching -GA • Model load balancing • Multi-regional deployments Traffic mediation & control • Azure AI Foundry & Azure OpenAI • OpenAI compatible models -GA • Responses API -GA • WebSocket’s for Realtime APIs • MCP server pass-trough - Soon • Expose APIs as built-in MCP server - Preview Developer velocity • Wizard policy configuration experience • Self-service with the Developer Portal • API Center Copilot Studio connector - Preview • Policy Toolkit Observability • Token counting per consumer • Prompts and completions logging -GA • Built-in reporting dashboard -GA Governance • Policy engine with custom expressions • API Center MCP server registry - Preview • Federated API Management GA GA GA Soon GA GA GA GA Preview Preview GA Preview New
7. APIM AI Gateway
8. /demo Expose existing API as MCP server
9. TechTalks Application TechTalks Consumer TechTalks Producer Message Broker Polyglot Programming
10. /demo APIM Auth Gateway for MCP servers
11. Azure API Management as Auth Gateway • Expose remote MCP servers in secure and scalable way • Security • API Management as remote MCP proxy safeguards organizational data through authentication and authorization • Scalability • Ensures system can handle load as the number of LLM interactions and external tools grows
12. MCP Client Auth Flow Azure API Management Your Auth Gateway For MCP Servers | Microsoft Community Hub
13. MCP will help your app/service grow Reach New Users Expose your capabilities through a variety of agents when the user needs them, getting users into your service. Accelerate User Tasks Agents can skip the learning curve with UI and get tasks done in seconds that would take the user tens of minutes. Agentic Capabilities for Less Integrate your servers into other agents if you don’t want to make your own. Easily make your own agent with MCP servers ready to go. Optimize Development Tools are for developers too! They can integrate into your development pipeline! Reducing toil and increasing speed. Easy Extensibility Provide an easy extensibility interface for services to integrate into your application, no new frameworks needed!
14. Summary • APIM streamlines the process of presenting APIs as MCP servers, enhancing security and scalability. • AI agents, like Copilot, are able to interact with enterprise APIs in a regulated manner, enabling new applications while maintaining oversight and safety. • OAuth 2.0 Authentication protects the MCP server, with APIM acting as the gatekeeper for the OAuth process. • The OAuth 2.0 framework utilizing Entra ID ensures that only permitted users are granted access to enterprise tools via MCP. • The MCP Inspector is a tool for developers aimed at testing and debugging MCP servers, akin to a visual debugger or “Postman” for MCP.
15. Examples Remote MCP APIM dotnet example Guide to building MCP Server in C#
16. Resources • Expose API as an MCP server • Azure API Management Auth Gateway for MCP servers • Connect once integrate anywhere with MCP • MCP C# SDK • GenAI Gateway Labs • MCP Inspector • Build 2025 Book of News • MCP servers
17. Slide deck https://speakerdeck.com/nileshgule/ https://www.slideshare.net/nileshgule/
18. Nilesh Gule ARCHITECT | MICROSOFT MVP “Code with Passion and Strive for Excellence” nileshgule @nileshgule Nilesh Gule NileshGule www.handsonarchitect.com https://www.youtube.com/@nilesh-gule
19. Q&A