What are the prerequisites to run this server?
.NET 9.0 SDK, an Azure subscription with an Azure OpenAI Service instance, and an Azure AD app registration with the `Application.Read.All` permission.
@ovaismehboob
基本信息
MCP Server that talks to Graph API
工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
An MCP server that connects to Microsoft Graph API, enabling an AI assistant to query and interact with Azure Active Directory/Entra ID resources. It includes a .NET Web API server and a Blazor WebAssembly client for AI-assisted chat about application registrations.
Configure appsettings.json with Azure OpenAI endpoint and Azure AD credentials, then run dotnet run from the MCP.Server and MCP.Client directories. Use the client’s “Test Connection” and “Test Graph API” buttons to verify connectivity, then chat with the AI about Azure AD resources.
.NET 9.0 SDK, an Azure subscription with an Azure OpenAI Service instance, and an Azure AD app registration with the `Application.Read.All` permission.
Set the `AzureOpenAI` section (Endpoint, DeploymentName, ApiKey) and `AzureAd` section (TenantId, ClientId, ClientSecret, Scopes) in `appsettings.json`.
The Microsoft Graph application permission `Application.Read.All` must be granted and admin‑consented.
Run the included `TestGraphPermissions.ps1` PowerShell script, or use the client’s “Test Graph API” button to diagnose permission issues.
Ensure your Azure OpenAI API keys and Azure AD client secrets are valid, confirm admin consent has been granted, and check CORS settings in the server’s `Program.cs` if the client cannot connect.

SSH MCP server for AI agents: remote commands, file transfer, log search and server audits through OpenSSH.

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.
OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.
评论