# Microsoft Graph & ARM

{% hint style="warning" %}
**Early Access** — Reach out to your Natoma representative for access.
{% endhint %}

**Type:** Community

**Source Type:** Repository

**Source:** [GitHub](https://github.com/merill/lokka)

**Description:** Microsoft Graph and ARM MCP server (powered by Lokka) provides AI assistants with access to Microsoft Graph and Azure Resource Manager. It enables querying users, groups, applications, devices, mailboxes, and Azure resources through an Entra ID app registration.

**Configuration Parameters:**

* **Tenant ID** \* - Directory (tenant) ID from your Entra app registration.
* **Client ID** \* - Application (client) ID from your Entra app registration.
* **Client Secret** \* (sensitive) - Client secret created under **Certificates & secrets**.

**Setup Steps:**

1. Open the [Microsoft Entra admin center](https://entra.microsoft.com/) and go to **Identity → Applications → App registrations → New registration**.
2. Name the app (e.g. `Natoma MCP`) and register. Copy the **Application (client) ID** and **Directory (tenant) ID**.
3. Under **API permissions**, add the Microsoft Graph application permissions you need (e.g. `Directory.Read.All`, `User.Read.All`, `Group.Read.All`) and grant admin consent. For Azure RM access, add **Azure Service Management → user\_impersonation** or use a service principal with appropriate Azure RBAC.
4. Under **Certificates & secrets → Client secrets → New client secret**, copy the secret **Value** immediately.
5. When creating the connection in Natoma, paste the Tenant ID, Client ID, and Client Secret and save.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.natoma.ai/apps/microsoft-graph-and-arm.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.