Sign in Book a demo
Back to Tools
Productivity & Docs OAuth
Build Your Agent View Documentation
microsoft-users logo

Microsoft Users MCP Tools for AI Agents

Let an agent identify the signed-in user, look up profiles, find managers, and list direct reports across your organization.

Available Tools

7 tools available in this integration

MicrosoftUsers.GetDirectReports

Get a user's direct reports from the organizational hierarchy.

MicrosoftUsers.GetManager

Get a user's direct manager from the organizational hierarchy.

MicrosoftUsers.GetUserManager

Get a user's direct manager from the organizational hierarchy.

MicrosoftUsers.GetUserProfile

Look up one or more users by email address, UPN, or user ID.

MicrosoftUsers.ListDirectReports

Get a user's direct reports from the organizational hierarchy.

MicrosoftUsers.ListUsers

Look up one or more users by email address, UPN, or user ID.

MicrosoftUsers.WhoAmI

Get information about the current user including name, email, job title,

Why agent-optimized tools matter

Built for intent, not API schemas

Ask the agent to "find the right manager and everyone who reports to them." Arcade picks the right directory actions without guessing email addresses, UPNs, or user IDs.

Up to 100x fewer tokens

Directory lookups return focused profile and hierarchy records, so the agent can map reporting lines without loading an entire organization's user directory into the model.

Complete the workflow end to end

Identify a user, read their profile, find their manager, list their direct reports, and return the reporting line through one toolkit designed around the complete directory task.

Make actions predictable and controlled

Arcade tools return structured results and useful errors across users and runs. Teams can apply scope restrictions, redaction, and approval policies so agents follow the same controls every time.

Securing Microsoft Users

The more capabilities agents get, the more useful they are. However, more capabilities bring more risks of undesired effects such as data loss and exfiltration.

This is why Arcade provides you with contextual rules that dictate how and when a tool is allowed to run. Arcade’s contextual access lets you govern tool visibility and behavior at every stage of execution and control who can see a tool, what inputs are allowed, and what comes back.

Learn about Contextual Access Policies

For Microsoft Users, you can implement some of these policies:

Access when tools are listed for a user
  • Decide which tools an agent is allowed to see at all. A tool that is never listed cannot be called, whoever is asking.
Pre-execution before each tool call
  • Inspect the inputs a call is about to run with, and block it or send it for human approval when they fall outside what the agent should do unsupervised.
Post-execution after the tool returns
  • Redact personal email addresses and phone numbers from MicrosoftUsers.GetUserProfile results before they reach the model, while retaining names, user IDs, and job titles.
  • Strip email addresses and phone numbers from MicrosoftUsers.GetDirectReports results, so an agent can map reporting lines without exposing employees' contact details.
  • Deny MicrosoftUsers.WhoAmI results when the current user's profile includes phone numbers or other personal contact fields, so those details never reach the model.

How to use Microsoft Users with your agent

Connect this toolkit to your MCP client and give your agent authenticated access to Microsoft user profiles and organizational hierarchy.

Your questions, answered

A Microsoft Users MCP server exposes Microsoft Graph user and organizational-hierarchy capabilities as structured actions an AI agent can call through the Model Context Protocol. After a user authorizes their Microsoft account, the agent can look up profiles, managers, and direct reports within the permissions granted.

Arcade provides the MCP access layer for these Microsoft Graph user capabilities. Arcade built this integration and adds per-user OAuth, credential brokering, approval and redaction policies, and a consistent way to reach the actions from supported clients.

Agents can identify the authorized user, look up profiles by email address, UPN, or user ID, find a user's manager, and list their direct reports. These actions are read-only; they do not update users, change reporting lines, or modify directory records.

Permissions depend on the actions and tenant consent. Current-user information can use User.Read, while looking up other users and organizational relationships may require delegated directory permissions such as User.ReadBasic.All, User.Read.All, or Directory.Read.All; request the narrowest permissions your workflow needs.

Yes. Each end user authorizes their own Microsoft account through OAuth. Actions run under that user's authorization, so the agent can access only the directory information allowed by that user's grant and tenant policies.

Yes. Contextual Access policies can require human approval before a call proceeds, redact fields from its response, or hide an action from the agent entirely. The listed Microsoft Users actions are read-only, so approval is usually about controlling access to directory information rather than preventing a write.

Arcade proxies Microsoft Graph calls and does not persist your content as part of normal tool execution. OAuth credentials are brokered and stored encrypted at rest, and the model never receives them.

Any framework or client that can connect to Arcade's MCP gateway or tool APIs works, including LangChain, OpenAI Agents, CrewAI, Claude Desktop, Claude Code, Cursor, Visual Studio Code, Microsoft Copilot Studio, and GitHub Copilot.

Arcade refreshes access while the user's Microsoft authorization remains valid. If it is revoked, rotated, or can no longer be refreshed, calls stop until the user reconnects their Microsoft account.

Calls are subject to Microsoft Graph throttling, tenant policies, and service limits. Build clients to handle throttling and retries; there is no separate toolkit-specific quota described here.

Ready to actually ship your agent?

Connect your agent to Microsoft Users with managed OAuth, agent-optimized tools and approval controls for consequential actions.

Build Your Agent Read the Microsoft Users Quickstart