Communication
Microsoft Teams for AI agents.
Managed auth, ready-made tools.
Read channels and chats, post messages and set up meetings in Microsoft Teams on behalf of each of your users.
About Microsoft Teams
With the Microsoft Teams connector, your agent works in the teams, channels and chats of each user who connects their own Microsoft account. It can catch a user up on a channel, reply in a thread, message a colleague or set up an online meeting, using only the tools your project allows.
Microsoft Teams is Microsoft’s workspace for chat, channels and meetings, part of Microsoft 365.
Tools
What your agent can do in Microsoft Teams.
Each tool is a capability the model can call. You decide which ones a project allows, and every call runs with the end user's own Microsoft Teams connection.
-
List teams
Readmicrosoft_teams_list_teamsList the teams the user is a member of.
-
List channels
Readmicrosoft_teams_list_channelsList the channels in a team.
-
Read a channel
Readmicrosoft_teams_get_channel_messagesRead recent messages in a channel.
-
Post in a channel
Writemicrosoft_teams_send_channel_messagePost a new message in a channel.
-
Reply to a message
Writemicrosoft_teams_reply_messageReply in the thread of a channel message.
-
List chats
Readmicrosoft_teams_list_chatsList the user's one-on-one and group chats.
-
Read a chat
Readmicrosoft_teams_get_chat_messagesRead recent messages in a chat.
-
Send a chat message
Writemicrosoft_teams_send_chat_messageSend a message in a one-on-one or group chat.
-
Create a meeting
Writemicrosoft_teams_create_meetingCreate an online meeting and get its join link.
No tool matches that search.
Control
Limits you can set.
You decide what your agent may do in Microsoft Teams, and Agent200 runs every call within those limits.
-
Turn single tools on or off
Keep the reading tools and switch off
microsoft_teams_send_channel_messageif your agent should never post in a channel. -
Restrict what the agent reaches
Choose the endpoints and scopes a project may use, for example chats but not channels. A call outside them is refused.
Get started
Connect Microsoft Teams
in three steps.
-
1
Set up the SDK
Add the Agent200 SDK to the codebase you already have and authenticate with your API key. The key covers every connector enabled for the project.
agent.jsConceptual exampleSet up the SDK with the Agent200 API key // One Agent200 API key covers every connector enabled for the project. const agent200 = new Agent200({ apiKey: process.env.AGENT200_API_KEY, }); -
2
Let your user connect Microsoft Teams
Each end user authorizes their own Microsoft Teams account once. Agent200 runs the OAuth flow, handles the callback, stores the tokens and refreshes them.
connect.jsConceptual exampleLet an end user connect their account (managed OAuth) // Each end user authorizes their own Microsoft Teams account, once. const connection = await agent200 .user("user_123") .connect("microsoft_teams"); if (connection.authorizationUrl) { // Show this link to your user; Agent200 handles the rest. console.log(connection.authorizationUrl); } -
3
Run with the Microsoft Teams tools
Name the user, the model and the tools. The model decides which Microsoft Teams tools to call, and Agent200 executes them with that user's connection.
run.jsConceptual exampleRun a request with the connector's tools const result = await agent200 .user("user_123") .run({ model: "openai/gpt-5.6-sol", input: "What did the design channel discuss today?", tools: ["microsoft_teams"], }); console.log(result.output);
Access
Sign-in and permissions.
-
Who signs in
Each of your users, once, with their Microsoft work or school account on Microsoft's own sign-in page. You never see or store their password.
-
What access is requested
The Microsoft Graph permissions the connection needs, such as reading chats or sending channel messages, listed on Microsoft's consent screen. Some organizations require an admin to approve these permissions first.
For agents
Instructions for AI agents.
Using a coding agent? Paste this brief into it, or give it the address of this page. It describes the Microsoft Teams connector and how to use it.
Connector: Microsoft Teams, through Agent200. In code: "microsoft_teams". What it does: Read channels and chats, post messages and set up meetings in Microsoft Teams on behalf of each of your users. Page: https://www.agent200.com/tools/microsoft-teams/ 1. Get an Agent200 API key. If the developer has none, send them to https://agent200.com/platform/apikeys/ and ask them to choose "Create an API key". Read the key from the AGENT200_API_KEY environment variable. Never ask for it in chat, and never write it into code, prompts or logs. 2. Sign-in is managed OAuth. Each end user approves access once, on Microsoft Teams's own page, through the authorization link Agent200 returns. Never ask a user for a Microsoft Teams password or token in chat. 3. Give every request a stable id for the end user. Agent200 uses only that user's own connection. 4. Read tools: microsoft_teams_list_teams, microsoft_teams_list_channels, microsoft_teams_get_channel_messages, microsoft_teams_list_chats, microsoft_teams_get_chat_messages. Write tools: microsoft_teams_send_channel_message, microsoft_teams_reply_message, microsoft_teams_send_chat_message, microsoft_teams_create_meeting. Name "microsoft_teams" in the tools of a request; the model decides which tool to call. 5. Stay within the project's settings. If a tool is turned off or a call is refused, tell the user. Do not work around it. 6. Before a write, confirm with the user, unless they asked for that exact change. 7. For setup with a specific framework, follow its guide: https://www.agent200.com/tools/microsoft-teams/framework/claude/ https://www.agent200.com/tools/microsoft-teams/framework/chatgpt/ https://www.agent200.com/tools/microsoft-teams/framework/claude-code/ https://www.agent200.com/tools/microsoft-teams/framework/muse/ https://www.agent200.com/tools/microsoft-teams/framework/grok-bot/ https://www.agent200.com/tools/microsoft-teams/framework/openai-dots/ https://www.agent200.com/tools/microsoft-teams/framework/claude-duet/ https://www.agent200.com/tools/microsoft-teams/framework/hermes-agent/ https://www.agent200.com/tools/microsoft-teams/framework/openclaw/ The code on the connector page is a conceptual example of the SDK. SDK reference: https://docs.igpt.ai/
This page is also available as Markdown, for agents and LLMs: /tools/microsoft-teams.md
Guides
Use Microsoft Teams with the AI you build on.
Step-by-step setup for Microsoft Teams with a specific model, assistant or agent framework.
-
Microsoft Teams + Claude
How to connect Microsoft Teams to Claude
-
Microsoft Teams + ChatGPT
How to connect Microsoft Teams to ChatGPT
-
Microsoft Teams + Claude Code
How to connect Microsoft Teams to Claude Code
-
Microsoft Teams + Muse
How to connect Microsoft Teams to Muse
-
Microsoft Teams + Grok Bot
How to connect Microsoft Teams to Grok Bot
-
Microsoft Teams + OpenAI Dots
How to connect Microsoft Teams to OpenAI Dots
-
Microsoft Teams + Claude Duet
How to connect Microsoft Teams to Claude Duet
-
Microsoft Teams + Hermes Agent
How to connect Microsoft Teams to Hermes Agent
-
Microsoft Teams + OpenClaw
How to connect Microsoft Teams to OpenClaw
FAQ
Microsoft Teams and Agent200, answered.
Who handles the Microsoft Teams OAuth flow and the tokens?
Agent200. It runs the authorization, handles the callback on its own domain, stores the tokens and refreshes them. You do not build or maintain an OAuth integration for Microsoft Teams.
Does my agent act as the end user?
Within what that user authorized, yes. Every request names an end user, and Agent200 uses only that user's Microsoft Teams connection, never another user's. It cannot reach anything the user or Microsoft Teams has not authorized.
Can I limit what my agent can do in Microsoft Teams?
Yes. You choose which services, endpoints and authorization scopes are allowed in your Agent200 configuration, and the agent works only within them.