MCP Graph API Demo
@ovaismehboob
MCP Graph API Demo について
概要はまだありません
基本情報
設定
ツール
ツールは検出されませんでした
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
概要
What is MCP Graph API Demo?
MCP Graph API Demo demonstrates the Model Context Protocol (MCP) with Azure Graph API to query application registrations in your Azure tenant. It uses a Blazor WebAssembly client that communicates with an ASP.NET Core server implementing MCP, allowing an AI-assisted chat interface to retrieve and present application registration data.
How to use MCP Graph API Demo?
Install .NET 9.0 SDK, configure Azure AD and OpenAI settings in the appsettings.json files (server and client), then start the server with dotnet run in MCP.Server and the client with dotnet run in MCP.Client. Open a browser and use the chat interface to ask questions about your Azure App Registrations.
Key features of MCP Graph API Demo
- Chat interface to query Azure tenant information
- Access to Graph API functions through MCP
- Semantic Kernel integration for LLM function calling
- Clean separation of LLM client and Graph API server
- Supports Azure OpenAI or OpenAI API
Use cases of MCP Graph API Demo
- List all app registrations in a tenant
- Get details for a specific app registration by ID
- Query permissions of an app registration
- Demonstrate MCP architecture with Graph API integration
FAQ from MCP Graph API Demo
What prerequisites are needed?
.NET 9.0 SDK, an Azure subscription with Application Registration permissions, and an Azure OpenAI resource or OpenAI API key.
How do I configure the server?
Edit MCP.Server/appsettings.json with your Azure AD tenant ID, client ID, client secret, and required scopes (User.Read, Application.Read.All).
Where does user data live?
Data is retrieved from Microsoft Graph API and processed on the server; the client only receives structured results and never holds raw Graph API data.
What transport or authentication does it use?
The server uses Azure AD authentication to call Microsoft Graph API; the client uses Azure AD for user authentication and an API key for OpenAI. Communication between client and server happens via standard HTTP.
Can I extend the Graph API capabilities?
Yes, add new function declarations in MCP.Server/Services/McpGraphService.cs and implement the logic in ExecuteFunctionAsync. The client's LLM automatically discovers and uses new functions.
「開発者ツール」の他のコンテンツ
DevDocs by CyberAGI 🚀
cyberagiincCompletely free, private, UI based Tech Documentation MCP server. Designed for coders and software developers in mind. Easily integrate into Cursor, Windsurf, Cline, Roo Code, Claude Desktop App
Hello World MCP Server (Reference Extension)
anthropicsDesktop Extensions: One-click local MCP server installation in desktop apps
test
prysmaticlabsGo implementation of Ethereum proof of stake
MCP Containers
metorialConnect any AI model to 1200+ integrations (MCP, CLI, API)
Serena
oraiosA powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent
コメント