About Demo of MCP capabilities
A C#/.NET 8 console demo that uses Azure OpenAI and Semantic Kernel to perform tasks through MCP. It is aimed at developers exploring MCP with an Azure OpenAI account and a local Node.js setup.
Key features
- 01Azure OpenAI task execution
- 02Semantic Kernel integration
- 03Console application on .NET 8
- 04Puppeteer MCP server dependency
Use cases
- 01Trying MCP-driven tasks with Azure OpenAI
- 02Exploring a Semantic Kernel MCP setup
MCP support
The application uses an MCP server, including @modelcontextprotocol/server-puppeteer, to provide task capabilities. The README does not detail the tools exposed.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEDemo of MCP capabilities
Using Azure OpenAI perform series of task using mcp server
How to run
- Replace the values in appsettings.json
- Run the following command to install the required packages:
dotnet restore - Compile and run the console application
Prerequisites
- Azure OpenAI account with access to the required models
- Node.js installed on your machine
Technologies
- Azure openai
- CSharp
- DotNet 8.0
- nugets
- Microsoft.SemanticKernel
- ModelContextProtocol
- Node.JS
- npx
- MCP Server
- @modelcontextprotocol/server-puppeteer
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.