A structured learning path for C# developers new to AI. Every guide uses code from this project — no abstract theory, just real examples you can open in Visual Studio right now. This version uses the official ModelContextProtocol v1.3.0 NuGet package with real JSON-RPC 2.0 stdio transport.
NexaFlowDemo is an ASP.NET Core 9 web application that shows how to add AI intelligence to a supply chain system. It is not a toy — it uses a real AI model (Anthropic's Claude) and covers the main patterns used in production AI systems.
This is the MCP Version: tools are hosted in a separate NexaFlowDemo.McpServer console app and invoked via the official ModelContextProtocol v1.3.0 NuGet package over real JSON-RPC 2.0 / stdio transport. The web app's ReactAgent connects to the McpServer subprocess through RealMcpClientService.
calling an LLM → having it reason and pick tools → giving it access to your database via real MCP tools → letting it search documents → persisting memory between conversations → triggering automated workflows.
Each guide below explains one of those patterns with plain English, C# analogies, and actual code excerpts from this project.
IServiceCollectionasync / await, Task<T>.Where(), .Select(), .ToDictionary()System.Text.Json, JsonDocumentHttpClient, PostAsJsonAsyncThe green boxes show the real MCP protocol layer. RealMcpClientService spawns NexaFlowDemo.McpServer as a subprocess and communicates via StdioClientTransport. RAG adds a document-search step before the LLM call. Memory stores facts across conversations. Workflows trigger automated actions when events fire.
What a Large Language Model actually is, how the Anthropic API works, how ClaudeService calls it, and what "tokens", "system prompt", and "context window" mean.
What an "agent" is (a think-act-observe loop), how ReactAgent routes tool calls through RealMcpClientService to the McpServer subprocess, and how IAsyncEnumerable streams steps in real time.
How the official Model Context Protocol lets Claude call your C# methods across a subprocess boundary, what [McpServerToolType]/[McpServerTool] attributes do, and how RealMcpClientService bridges the web app to the McpServer.
What embeddings are, what a vector store does, how RagPipeline retrieves relevant documents and injects them into the prompt, and how the document_search MCP tool exposes this to Claude.
Full architecture overview, feature map, file layout, MCP migration notes, CLI reference, and the complete list of test scenarios.
dotnet run in NexaFlowDemo.Web) and try the chat UI — you will see the ReAct loop live.C:\Guy\Notes\Claud Projects\Agentic Baiic 03_SupplyChain_ClaudeLiveKey_MCP_Version\NexaFlowDemo.McpServer subprocess is launched automatically by RealMcpClientService when the first tool call is made — you do not need to start it manually.