AI agents call get_chat_messages to retrieve information from Teams without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a query operation that fetches existing chat messages without creating, modifying, deleting, or executing any actions. It has no side effects and simply returns information from the Teams service.
From the tool's definition Tool description states 'Retrieve recent messages from a specific chat conversation' with 'Returns message content, sender information, and timestamps.' The verb 'Retrieve' and the read-only nature of returning existing message data without modification…
Attacks that exploit this kind of access
Retrieve recent messages from a specific chat conversation. Returns message content, sender information, and timestamps. It is categorised as a Read tool in the Teams MCP Server, which means it retrieves data without modifying state.
Register the Teams MCP server in PolicyLayer and add a rule for get_chat_messages: 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. Nothing to install.
get_chat_messages 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 get_chat_messages 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 get_chat_messages. 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.
get_chat_messages is provided by the Teams MCP server (@floriscornel/teams-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.