How to connect your systems to AI Tools with MCP Servers
summary
Shows how to build an MCP server in C# / ASP.NET Core using JSON‑RPC 2.0 over HTTP and the Model Context Protocol so AI agents like GitHub Copilot can call real services. Demonstrates an issues API with concrete tools getAllIssues, getIssueById, changeStatus and addComment, including input/output schemas, readOnly flags, enum values and structured outputs. Covers hosting options, auth, using the MCP inspector to view initialize/capabilities calls, and how the MCP server packages and exposes metadata for reliable agent actions.
AI-written summary · about
chapters (13)
- 0:00Introduction to MCP
- 3:27Model Context Protocol basics
- 5:53MCP server capabilities
- 7:20Demo setup overview
- 9:08Creating MCP server in C#
- 14:11Defining MCP server tools
- 17:37Testing the MCP server
- 22:34Integrating with GitHub Copilot
- 25:40Enhancing tool descriptions
- 30:14Finalizing the MCP server
- 33:34Live demo results
- 35:45Adding prompts and resources
- 37:07Conclusion and resources
related talks
01h 01m.NET Meets MCP: Build Your Own AI-Powered Service with C#
46mMCP for LLM Agents, Infrastructure APIs & Data Services
33mThe Model Context Protocol: Connecting AI to Everything
25mMaking AI Personal: Building Context-Rich AI Tools with MCP
25mTools in your AI's Toolbox : An introduction to MCP Servers
35mMCP in Action: Real-World Use Cases & Design Patterns
16mDriving agentic innovation w/ MCP as the backbone of tool-aware AI
36mPutting AI Agents to Work: A New Era of Open Source Connectivity with MCP