Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@agentic-msteams-mcp send a Teams message to #general: 'Deployment complete'"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A self-hosted Microsoft Teams MCP server that serves as an agnostic human-in-the-loop gateway for AI agents.
This project implements a dual-surface architecture to allow AI agents to interact with humans via Microsoft Teams without requiring the agent to have direct Graph API access or complex bot logic.
v0.4.0 provides a comprehensive suite of tools for agents to interact with humans via Microsoft Teams, including notifications, asynchronous questions, and formal approval workflows.
msteams_send_notification: Sends one-way alerts.
msteams_ask_user: Poses structured questions; returns request_id.
msteams_get_user_reply: Tracks responses to asks.
msteams_request_approval: Requests a formal binary decision (Approve/Reject).
msteams_get_approval: Checks the state of an approval request.
Related MCP server: call-a-human-mcp
The primary interface for AI agents. It exposes a strictly limited toolset of six tools:
msteams_health_check: Verifies server connectivity.
msteams_send_notification: Sends one-way alerts to allowlisted users/channels.
msteams_ask_user: Requests information from an allowlisted user.
msteams_get_user_reply: Checks the state of a requested reply.
msteams_request_approval: Initiates a formal approval request.
msteams_get_approval: Retrieves the decision for an approval request.
A lightweight FastAPI app that acts as the webhook receiver for Microsoft Teams. It is designed to be hosted behind a proxy/gateway.
The server explicitly denies any arbitrary Graph API operations. All interactions are gated through specific, high-level tools.
Notifications and Asks are only delivered to IDs defined in the MSTEAMS_ALLOWED_USER_IDS or MSTEAMS_ALLOWED_CHANNEL_IDS environment variables. If an ID is not listed, the request is rejected immediately.
Every attempt to notify or ask a user is logged to a local audit file (MSTEAMS_AUDIT_LOG_PATH).
Privacy: Log entries contain metadata and fingerprints but NEVER include the actual message or question body.
Stability: Uses SHA-256 deterministic fingerprinting for audit evidence.
By default, MSTEAMS_NOTIFICATION_DRY_RUN=True. In this mode, the server validates all requests and logs them to audit but does not actually call the Microsoft Graph API. NOTE: Real Teams/Graph delivery is currently not implemented; dry-run is the intended safe default for current versions.
Variable | Default | Description |
|
| Bind address for the HTTP surface. |
|
| Port for the HTTP surface. |
|
| Comma-separated list of allowlisted User IDs (Required). |
|
| Comma-separated list of allowlisted Channel IDs. |
|
| If true, no real Graph API calls are made. |
|
| Path to the append-only audit log file. |
The server provides two distinct modes:
1. MCP Stdio Mode (for AI Agents)
python -m agentic_msteams_mcp.main --mcp2. HTTP Surface Mode (for Teams Webhooks)
python -m agentic_msteams_mcp.main --httpThe server is provided as a Docker image for consistent runtime environments.
docker build -t agentic-msteams-mcp .
docker run -p 8000:8000 -e MSTEAMS_ALLOWED_USER_IDS="user1,user2" agentic-msteams-mcp --httpThis server cannot be deployed
MCP server for building and testing AI agents with multi-model experimentation and insights.
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
Self-hosted MCP gateway: turn any API, database or MCP server into AI connectors — no code.
The MCP server for Azure DevOps, bringing the power of Azure DevOps directly to your agents.