MCP Dotnet Samples

Model Context Protocol (MCP) .NET sample library, demonstrating how to use the MCP protocol to standardize the context interaction of large language models (LLMs) in .NET applications. It includes examples such as a YouTube subtitle extractor, supports flexible switching of LLM providers, and enables the construction of AI workflows.

Developer tools Artificial intelligence chatbots #AI protocol #LLM integration #Data standardization #Workflow construction .C#

rating : 2.5 points

downloads : 36

update time : 2025-04-28

What is Model Context Protocol (MCP)?

MCP is an open protocol used to standardize the way applications provide context to large language models (LLMs). It's like USB - C, providing a unified way to connect different data sources and tools.

How to use the MCP server?

Simply install the MCP server and configure your data sources to start interacting with LLMs. It supports multiple programming languages and platforms.

Applicable scenarios

Suitable for enterprise applications, development tools, and data processing systems that need to integrate AI models.

Main features

Data source integrationSupports multiple data sources, such as databases, APIs, and file systems.

Cross - vendor compatibilitySupports multiple LLM providers for easy switching.

Security guaranteeBuilt - in security mechanisms protect sensitive data.

Advantages and limitations

Advantages

Standardized interface simplifies the development process.

Supports flexible switching of LLM providers.

Enhances data security and privacy protection.

Limitations

Requires a certain technical foundation for deployment and configuration.

Some advanced features may depend on the support of specific providers.

How to use

Install the MCP server

Download and install the MCP server software.

Initialize the configuration

Run the initialization command to generate the default configuration file.

Connect to data sources

Add the required data source connection information.

Usage examples

Extract YouTube video subtitlesDemonstrate how to extract subtitles from a YouTube video and pass them to an LLM for analysis.

Frequently Asked Questions

Does the MCP server support multiple languages?

How to ensure data security?

Related resources

MCP official documentation

Learn the detailed description of the MCP protocol.

GitHub code repository

View the open - source code of the MCP project.

🚀 Model Context Protocol (MCP) .NET Sample Project

🚀 Introduction

Welcome to the Model Context Protocol (MCP) .NET sample repository! This collection of samples demonstrates how to leverage the Model Context Protocol in .NET applications.

MCP is an open protocol designed to standardize the way applications provide context to Large Language Models (LLMs). Think of MCP as the USB-C port for AI applications—it offers a standard way to connect AI models to different data sources and tools.

With MCP, you can:

Utilize off-the-shelf integrations that can be directly used by your LLM.
Flexibly switch between different LLM providers and vendors.
Follow best practices to ensure the security of your data.
Build LLM-based agents and complex workflows.

This repository contains .NET samples, ranging from building your own MCP implementation to integrating with Azure services.

📋 Sample Projects

Sample Name	Description
YouTube Subtitles Extractor	A remote MCP server that can extract subtitles from any given YouTube video URL.

🛠️ Quick Start

Detailed information on how to set up and run the samples will be provided in each sample directory.

📚 Learning Resources

🚶♀️ Next Steps

Contribution Guidelines

This project welcomes contributions and suggestions. Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit the CLA website.

When you submit a pull request, a CLA bot will automatically determine whether you need to provide a CLA and decorate the PR appropriately (e.g., status check, comment). Simply follow the instructions provided by the bot. You will only need to do this once for all repositories using our CLA.

This project has adopted the Microsoft Open Source Code of Conduct. For more details, visit the Code of Conduct FAQ or contact us via opencode@microsoft.com with any additional questions or comments.

Trademarks

This project may contain trademarks or logos for projects, products, or services. Authorization to use Microsoft trademarks and brands is subject to Microsoft's Trademark and Brand Guidelines. Modified versions of Microsoft trademarks or logos used in our projects must meet Microsoft's sponsorship eligibility and not cause confusion. Any use of third-party trademarks or logos must comply with the policies of the respective third party.