What runtime and dependencies are required?
The project is a .NET console application built with C#. You need the .NET SDK installed to build and run it (using the `dotnet` command).
@MartinM85
基本信息
Model-context-protocol (MCP) server for the Microsoft Graph API in C#
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"graphApi": {
"command": "dotnet",
"args": [
"run",
"--project",
"path/to/folder/with/console_project",
"--no-build"
],
"env": {
"TENANT_ID": "<tenant_id>",
"CLIENT_ID": "<client_id>",
"CLIENT_SECRET": "<client_secret>",
"NATIONAL_CLOUD": "Global"
}
}
}
}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 (Model Context Protocol) server written in C# that enables AI assistants (such as Claude or Azure OpenAI) to interact with the Microsoft Graph API and answer questions about your Microsoft Entra tenant.
Register an Entra ID application with at least User.Read.All permission, then configure the server in claude_desktop_config.json with your tenant ID, client ID, client secret, and optional national cloud endpoint. Build the solution, and the MCP server will be automatically discovered by the Claude Desktop app.
The project is a .NET console application built with C#. You need the .NET SDK installed to build and run it (using the `dotnet` command).
The server uses an Entra ID application with a client secret (app‑only authentication). You must grant at least the `User.Read.All` application permission and provide the tenant ID, client ID, and client secret in environment variables.
Yes. Set the `NATIONAL_CLOUD` environment variable to `Global`, `US_GOV`, `US_GOV_DOD`, `China`, or `Germany` to target the corresponding Microsoft Graph endpoint.
The server uses command‑line stdio (standard input/output) for transport, as configured in `claude_desktop_config.json`. Authentication is always via Entra ID client credentials.
When using Claude Desktop, logs can be found in `%APPDATA%\Claude\logs` on Windows.

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

The tools your AI needs to make your games. Turn prompts into production-ready game assets — animated characters with their weapons attached, seamless textures, terrain, VFX, HUDs — and playable game kits Unity, Godot, U

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP

Know when your AI agents, cron jobs and CI pipelines fail, stall or go quiet. Your agent sets up monitors from a plain description, tells you what is broken and why, reads run history and traces, and writes notes on inci
OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.
评论