Search for messages across all Teams channels and chats using Microsoft Search.
AI agents call teams_search_messages to retrieve information from Microsoft Teams without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries message data across Teams without side effects. It is a Read operation. Severity is high (not critical) because search across all channels and chats can expose sensitive information including private messages, confidential discussions, and data from channels the user may not have direct access to—creating significant privacy and information disclosure risk if misused by an agent.
From the tool's definition Tool name contains 'search' and description states 'Search for messages across all Teams channels and chats' with no mention of modification, deletion, or execution.
Attacks that exploit this kind of access
Search for messages across all Teams channels and chats using Microsoft Search. It is categorised as a Read tool in the Microsoft Teams MCP Server, which means it retrieves data without modifying state.
Register the Microsoft Teams MCP server in PolicyLayer and add a rule for teams_search_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 Microsoft Teams. Nothing to install.
teams_search_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 teams_search_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 teams_search_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.
teams_search_messages is provided by the Microsoft Teams MCP server (microsoft-teams-mcp-server). 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 →