Read Microsoft Teams Messages with Claude on Mac — With Your Microsoft 365 Account
In short: Let Claude, Cursor, VS Code or ChatGPT read and send your Microsoft Teams chats and channels on your Mac. LMCP uses the work or school Microsoft 365 account you connect, through Microsoft Graph — no Azure app registration of your own and no API key. Reading channel messages can need your administrator's approval.
Average 5.0 out of 5 · Ratings: 2See all reviews →
“The no-tokens part is huge. Setting up Graph API and dealing with auth flows is what usually kills these setups for me before I even start.”
Lisa S.“This is AMAZING! My daily work can all be managed from my key apps now. The OmniFocus integration was the missing piece.”
Steve H.
To let Claude read your Microsoft Teams chats on a Mac, install LMCP and connect your Microsoft 365 work or school account — LMCP is a local MCP server, and on a Mac it reads and sends Teams through Microsoft Graph with the account you connect. You sign in once with a code: there is no Azure app registration of your own and no API key to create. Your AI can list chats and channels, read history, search across your conversations and check call history.
What You Can Access
Through LMCP, your AI assistant can:
- List your chats — see all your 1:1 and group conversations with recent activity
- Read chat messages — get recent messages from any chat
- List your teams and channels — see which Teams workspaces and channels you belong to
- Read channel messages — get messages from any channel you have access to
- Search messages — find something across all your chats at once
- Check call history — direction, participants and duration of your Teams calls
- Send chat messages — reply or start a conversation; the first call returns a preview and a second call with confirm=true sends it
- Post channel messages — write in a channel, with the same preview and confirmation
Preview and confirmation behavior depends on the tool, platform and AI client. Check the tool requirements and review the intended action before authorizing a real call.
If the selected AI client uses a cloud AI provider, that provider can receive and process the Teams message content requested for the task under its own terms.
Connect Your Microsoft 365 Account First
Reading and sending take the same path: Microsoft Graph, through a Microsoft 365 account you connect. To read or send Teams, connect your account first. It must be a work or school account: personal Microsoft accounts (@outlook.com, @hotmail.com) do not have Teams. You can connect several accounts.
In practice: ask your AI to run connect_m365_account and sign in with the code it shows you. After that, your AI can read chats and channels and send chat and channel messages (check its current preview and confirmation requirements before authorizing a call). Reading channel messages can require an administrator of your organization to approve a permission; when that is the case, the answer says so instead of failing silently.
Without any connected account: from LMCP 3.0.420, if no Microsoft 365 account is connected at all, the Teams read tools on a Mac fall back to the local cache of the Teams desktop app. This needs Full Disk Access for LMCP, can be hours or days behind and is read-only; sending still needs a connected account.
How to Install
Download LMCP and install it:
- Open the downloaded
LMCP-Installer.dmgfrom your Downloads folder - Open LMCP Installer — it installs Local MCP to Applications for you (no dragging)
- Open Local MCP from your Applications folder — it appears in your menu bar
Takes about 30 seconds. Your AI clients are configured automatically.
After installation, restart your AI client so it picks up the new MCP tools:
- Claude Desktop — quit completely (Cmd+Q) and reopen
- Cursor — restart the editor
- VS Code — reload the window (Cmd+Shift+P → “Reload Window”)
- ChatGPT / Devin Desktop (formerly Windsurf) — restart the application
Then connect your account as described above. The Teams desktop app does not need to be installed or running for LMCP to read or send.
Example Prompts
Once connected, try these prompts with your AI assistant:
- “What did the team discuss today in the General channel?” — reads recent channel messages and summarizes the key points
- “Show my conversation with Marco” — lists recent messages from a specific chat
- “Find any messages about the deployment deadline” — searches through your chats and channels
- “Summarize what I missed in Teams this morning” — aggregates messages across multiple conversations
- “Which channels have new messages today?” — scans your teams for recent activity
- “What did the design team say about the new mockups?” — finds and summarizes relevant discussion
Your AI assistant is especially useful for catching up on busy channels. Instead of scrolling through hundreds of messages, you can ask for a summary of what matters.
Real-World Workflows
Reading individual messages is just the start. The real value comes when you ask your AI assistant to synthesize information across conversations and take action:
Daily standup summary
Read the engineering channel messages from today, extract what each person is working on, identify blockers, and create a summary note.
Instead of scrolling through a busy channel, your AI reads everything, organizes it by person, and highlights blockers. Perfect for managers who need to stay informed without reading every message.
Meeting prep from Teams
Check what the team discussed about Project X in the last week across all channels, summarize the key decisions, and list open questions I should bring up in tomorrow's meeting.
Your AI scans multiple channels, finds relevant discussions, and prepares a briefing document. You walk into the meeting fully informed instead of scrambling to catch up.
Create tasks from chat
Go through my Teams chats from today, find anything that looks like a task or commitment I made, and list them with who asked and when.
Conversations in Teams often contain implicit commitments — “I'll look into that” or “let me send you the doc.” Your AI finds these and surfaces them so nothing slips through.
Project documentation
Read the last 50 messages in the #architecture channel, extract decisions made about the API design, and create a Word document with the architecture decisions log.
Important decisions often get buried in chat history. Your AI extracts them, structures them into a proper document, and saves it so your team has a permanent record.
LMCP also connects your AI assistant to email, Outlook, Calendar, Contacts, OneDrive, and local files. See the full list of guides or learn more at local-mcp.com.
Why Teams on Mac needs a Microsoft 365 account
Your Teams conversations live on Microsoft's servers, and Microsoft Graph is the official way to read them programmatically. LMCP makes the integration for you: you connect your account once, and LMCP calls Graph on your behalf, so you do not register an Azure AD app or manage tokens yourself.
Limitations
- A connected work or school Microsoft 365 account is required — for reading and for sending. Personal Microsoft accounts do not have Teams.
- Channel messages can need administrator consent — if your organization has not approved the permission, the answer says so.
- Reads cover recent activity — a read looks at your most recent chats and newest messages, not your full history; when an answer is cut short it says so. Search returns at most 100 results, in order of relevance.
- Call history is limited — it lists calls and meetings that ended in your 50 most recent chats; Microsoft does not say who started a call or whether it was answered.
- A network connection is needed — Teams is read from Microsoft 365, not from your disk.
- Send only, no edit or delete — LMCP can send new chat messages and channel posts (the first call returns a preview, and a second call with confirm=true sends it) but cannot edit or delete existing ones
- Multiple accounts — you can connect more than one Microsoft 365 account
- Without an account, reads fall back to the local cache — if no Microsoft 365 account is connected, the read tools use the Teams desktop app's local cache, which needs Full Disk Access, can be hours or days behind and is read-only. Sending still needs a connected account.
Frequently Asked Questions
How do I let Claude read my Teams chats on a Mac?
Install LMCP, then ask your AI to connect your Microsoft 365 account (connect_m365_account) and sign in with a work or school account. Reading chats works through Microsoft Graph with that account.
Can Claude send Teams messages?
Yes — both a direct chat message and a channel post, with the same connected account. LMCP shows a preview first and sends only after you confirm. It cannot edit or delete messages.
Do I need a Microsoft 365 account to read Teams on a Mac?
Yes. Teams on a Mac is read through Microsoft Graph with a connected work or school Microsoft 365 account; personal Microsoft accounts do not have Teams. You do not register an Azure app of your own or create an API key.
Does it need admin approval to read Teams?
Reading channel messages can require an administrator of your organization to approve a permission; if it is missing, the answer says so. What else your organization restricts depends on its own settings.
Does the Teams desktop app need to be running?
No. LMCP reads and sends through Microsoft 365, so the Teams desktop app does not need to be installed or running. A network connection is needed.
Ready-Made Recipes
Copy-paste workflows that use Teams together with your other apps:
- Find every unanswered client request across WhatsApp, Slack, Teams & email
- Have your AI prep you for your next meeting
Related Guides
Comments
Questions and experiences welcome — comments are reviewed before they appear.