What does search_m365_directory return?

It returns Microsoft 365 users matching your name or email query, including each person's display name, email address, job title and department, so you can identify and reach the right colleague.

Do I need API keys or admin access to use it?

No separate API keys are required. LMCP uses your own authenticated Microsoft 365 connection on your Mac. You only see directory entries your account is already permitted to see in your organization.

Can ChatGPT or Perplexity use this tool too?

Yes. Desktop clients like Claude Desktop and Cursor auto-configure over local stdio, while web AIs such as ChatGPT, Claude.ai, Grok and Perplexity connect through the LMCP Cloud Relay connector.

Search Your Microsoft 365 Directory with AI on Mac

The search_m365_directory tool lets your AI assistant look up people in your organization's Microsoft 365 directory by name or email, right from your Mac. It returns matching users along with their job title and department, so you can find the right colleague without opening the admin center or Outlook's address book. A typical prompt looks like: "Find everyone named Sarah in our Microsoft 365 directory and tell me their titles and departments." The AI runs the search through your local M365 connection and hands back a clean list.

This is part of LMCP, a free, native macOS MCP server with 150+ tools that connects AI assistants to your real apps and accounts. Download LMCP to get started.

Which AI agents work?

search_m365_directory works with every major AI assistant that speaks the Model Context Protocol:

Claude Desktop, Cursor, VS Code (GitHub Copilot), Windsurf and Zed — desktop clients that auto-configure over local stdio.
ChatGPT, Claude.ai (web), Grok and Perplexity — web AIs that connect through the LMCP Cloud Relay connector.

Desktop clients discover the tool automatically once LMCP is installed; web AIs connect securely via the relay so they can reach the same directory data living on your Mac.

Automation

Directory lookups rarely stand alone — they feed the next step. Because the AI can chain tools, search_m365_directory becomes the lookup stage of bigger workflows:

Find a person, then draft and send them an email or a Teams message.
Resolve a name to an email address, then schedule a calendar invite with the right attendee.
Pull everyone in a department, then build a contact list or a distribution summary.
Confirm a colleague's title before generating an org chart or a project assignment.

You describe the goal in plain English and the AI orchestrates the steps for you.

Context

Unlike a generic chatbot that only knows public information, the AI here works with your real Microsoft 365 directory. It sees the actual people in your tenant — their current titles, departments and email addresses — so answers reflect your organization today, not a stale guess. That live context is what turns "who handles procurement?" into a precise, named answer.

Productivity

Hunting through Outlook's address book or asking IT for someone's department breaks your flow. With search_m365_directory you stay in your AI chat: ask once, get the title, department and email in seconds, and immediately act on it. For anyone who routes requests, builds teams, or just needs to find the right person fast, it collapses a multi-minute hunt into a single sentence — dozens of times a week.

Privacy & GDPR

Everything runs locally on your Mac. LMCP queries your Microsoft 365 directory through your own authenticated session and returns results straight to your AI client — no copy of your org's directory is stored on any LMCP server, and there are no third-party API keys to manage. Your colleagues' data never sits in a cloud middleman. Read more about how LMCP is GDPR-compliant by architecture.