Microsoft Teams
Put your AI agents and workflows in Microsoft Teams: a bot that hears messages and commands, replies in the thread and sends adaptive cards with buttons.
Book a demo
Microsoft Teams for AI agents and workflows.
engini puts a bot in Microsoft Teams. Your agents and workflows hear messages and commands, reply in the thread, and send adaptive cards whose buttons start the next step. People ask about an order, an invoice or a ticket where they already work, and the answer comes from your systems of record. Connect from Claude, ChatGPT or Cursor over MCP, from your code, or build in Workflow Studio.
Cursor, your code
audit log

in engini
What your agent can do in Teams. Hear, answer and hand off.
The Teams tools in engini. The bot listens for messages, commands and card clicks, and answers with messages, threaded replies and adaptive cards. What it can do in your other systems is set by the tools you give the agent behind it.
Write
Post a message to a chat or channel.
Reply in the thread that started the work.
Send a card with fields and buttons.
Triggers
Someone messages the bot.
Someone sends the bot a command.
Someone asks the bot for help.
Someone clicks a button on a card the bot sent.
A trigger starts a workflow, and a workflow can include an AI agent step. In Code, a trigger delivers the event to your own endpoint.
Connect your AI agent to Microsoft Teams. Four ways in, one set of permissions.
Claude, ChatGPT, Cursor
Create an MCP server in engini with your Microsoft Teams connection and only the tools you choose. Add its address to your client and sign in through engini. There is no key to copy.
MCP client setup →Python and TypeScript
Hand your agent a toolset of Microsoft Teams tools. The SDK gives OpenAI and Anthropic models the tools in the format they expect and runs the ones they pick.
SDK guide →For coding agents
The engini CLI connects Microsoft Teams and runs its tools from a terminal, with machine-readable output, so an AI coding agent can drive it without getting stuck.
CLI guide →Any language
Every Microsoft Teams tool is an endpoint. Call it with exact inputs from a scheduled job or a sync, with no model in the loop.
API reference →.cursor/mcp.json. Claude Code: claude mcp add.// .cursor/mcp.json: Cursor, connected to Microsoft Teams through engini
{
"mcpServers": {
"engini-microsoft-teams": {
"url": "<your engini MCP server address>"
}
}
}
Create the MCP server in engini with your Microsoft Teams connection and the tools this agent may use, then paste its address. The client signs in through engini on first use. Claude, VS Code and other clients take the same address: see the MCP client setup guide.
Each request runs through the Microsoft Teams tools in the agent's toolset or MCP server. If a tool is not allowed, the agent cannot call it.
What teams build on Microsoft Teams. Agents and workflows, across systems.
Ask the ERP from Teams
Someone asks the bot about an order or an invoice. An agent reads NetSuite or SAP and replies in the thread. Its toolset holds read tools only.
Time off, in chat
The bot tells people their balances and files their time off requests in Workday.
Cards that start the next step
A workflow sends an adaptive card with the details; a click on its button starts the next workflow.
Help desk in the channel
A message to the bot becomes a Jira issue or a Zendesk ticket, and the reply carries its number.
Every integration runs both ways, so any of these flows can also run in reverse. These are examples, not the limit: any flow between Microsoft Teams and another system engini connects is available.
You decide what each agent may do in Microsoft Teams. engini enforces it on every call.
Only the tools you allow
A toolset lists the Microsoft Teams tools an agent may call and the connection each one uses. Give one agent read tools only and another the write it needs. engini refuses any call outside the toolset.
Scoped when you set them up
An MCP server exposes only the connections and tools chosen when it is created, and engini shows who uses each server.
Whose permissions apply
Connect a person's own Microsoft Teams account and engini acts as that person, with their Microsoft Teams permissions. Use a shared integration account and it acts as that account. Every run is recorded under the user who started it.
Kept out of prompts
Your agent never needs your credentials: engini stores them and adds them when it runs each call, so keys stay out of prompts and tool inputs.
Every call on record
Every call lands in History and the audit log, which you can export or stream to your SIEM.
Test before production
Workspaces keep teams apart, and development, staging and production environments keep a test agent away from live data.
Connect Microsoft Teams in three steps. Then decide what each agent may do.
Sign in to Microsoft Teams
Add a Teams connection and sign in with OAuth 2, through engini or your own Microsoft app, then add the bot to the chats and channels it should serve.
Choose the tools
Add the connection to an MCP server or a toolset with only the tools each agent needs.
Build or ask
Use the connection as a step in a workflow, or ask your agent to work in Microsoft Teams from Claude, ChatGPT, Cursor or your own code.
Microsoft Teams and engini. Straight answers.
Can an AI agent write to Microsoft Teams, or only read?
Both. the bot posts messages, threaded replies and adaptive cards; what it can change in other systems depends on the tools you give the agent behind it. Whether a given agent may use them is up to you: give it a toolset or an MCP server with read tools only, and it cannot call the rest.
Does the agent act as me in Microsoft Teams?
The bot speaks as itself. What it can do in other systems runs through the connections in its toolset or MCP server. Every run is recorded under the person who started it.
Can a change in Microsoft Teams start work?
Yes. A message, a command, the help command or a click on a card button starts a workflow, and that workflow can include an AI agent step.