Get unread status. Without conversationId: one bulk API call over your recent conversations (up to 200), returns separate lists of unread chats and channels (conversationId, displayName, lastMessageFrom) plus counts. With conversationId: unread count for that chat/channel using read horizon vs re...
AI agents call teams_get_unread to retrieve information from Teams MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about unread messages and conversation status without creating, modifying, deleting, or executing any operations. It is a pure read operation that queries the state of Teams conversations. Low severity due to minimal blast radius—an agent misuse would only expose conversation existence and unread status information, not message content or broader Team operations.
From the tool's definition Tool name 'teams_get_unread' and description 'Get unread status' indicates data retrieval only. Retrieves 'unread chats and channels' and 'unread count' with no modification capability. Returns informational data about conversation state.
Attacks that exploit this kind of access
Get unread status. Without conversationId: one bulk API call over your recent conversations (up to 200), returns separate lists of unread chats and channels (conversationId, displayName, lastMessageFrom) plus counts. With conversationId: unread count for that chat/channel using read horizon vs recent messages. It is categorised as a Read tool in the Teams MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Teams MCP Server MCP server in PolicyLayer and add a rule for teams_get_unread: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Teams MCP Server. Nothing to install.
teams_get_unread is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the teams_get_unread rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for teams_get_unread. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
teams_get_unread is provided by the Teams MCP Server MCP server (m0nkmaster/msteams-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →