About WinFormsApp-MCP
WinFormsApp-MCP is a Windows Forms desktop application demonstrating Semantic Kernel integration with MCP. It provides tool access to GitHub, GitLab, and filesystem operations for ChatGPT models.
Key features
- 01GitHub and GitLab repository access
- 02Filesystem operations
- 03OpenAI ChatGPT model support
- 04Configurable API keys and model selection
Use cases
- 01Interact with code repositories via AI
- 02Manage files with language models
- 03Explore MCP and Semantic Kernel integration
MCP support
The client connects MCP services through Semantic Kernel, exposing GitHub, GitLab, and filesystem tools to ChatGPT models.
Details
From the project READMEWinFormsApp-MCP
WinFormsApp-MCP is a Windows Forms application demonstrating Semantic Kernel with Model Context Protocol (MCP). It provides tool functionality for GitHub, GitLab, and filesystem operations, and works with ChatGPT models.
Overview
This application showcases the integration of large language models (LLMs) with Microsoft's Semantic Kernel framework, allowing models to interact with local and remote resources through the Model Context Protocol (MCP).
The implementation is based on the step-by-step guide from the Microsoft Semantic Kernel blog.

Features
-
LLM Support:
- OpenAI (ChatGPT) models
-
Tool Functionality:
- GitLab repository access
- GitHub repository access
- Filesystem operations
- Context-aware interactions
Requirements
- .NET 8.0 or later
- API key for OpenAI
Configuration
The application provides a settings interface to configure:
- API key
- Model selection
- GitLab integration settings
- Filesystem access controls
You can also configure the application using environment variables:
string? apiKey = Environment.GetEnvironmentVariable("OpenAI__ApiKey");
string? modelId = Environment.GetEnvironmentVariable("OpenAI__ChatModelId") ?? "gpt-4o-mini";
The application will check for these environment variables:
OpenAI__ApiKey: Your OpenAI API keyOpenAI__ChatModelId: The model to use (defaults to "gpt-4o-mini" if not specified)
Getting Started
- Clone the repository
- Open the solution in Visual Studio
- Add your API key in the Settings dialog or set it as an environment variable
- Configure MCP settings as needed
- Run the application
MCP Resources
- Anthropic MCP Announcement - Original introduction of the Model Context Protocol
- MCP Servers Directory - Directory of available MCP servers
- Model Context Protocol Documentation - Official MCP documentation
- mcpdotnet NuGet Package - .NET library for Model Context Protocol
- Semantic Kernel Documentation
- Semantic Kernel GitHub Repository
- Integrating MCP Tools with Semantic Kernel Guide
License
[Include your license information here]
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.