AI agents call teams_search_messages to retrieve information from Sage MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a Read operation: it searches and retrieves messages from Microsoft Teams, producing no side effects. Severity is high rather than low because message content often contains sensitive information (credentials, personal data, business intelligence), making unauthorized search access a significant data exposure risk despite being read-only.
From the tool's definition Tool name is 'teams_search_messages' and description states 'Search across messages in the user' — this retrieves/queries message data without modifying it.
Documented attack patterns abuse exactly the kind of access teams_search_messages gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Sage MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for teams_search_messages:
{
"version": "1",
"default": "deny",
"tools": {
"teams_search_messages": {}
}
}teams_search_messages is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Search across messages in the user. It is categorised as a Read tool in the Sage MCP MCP Server, which means it retrieves data without modifying state.
Register the Sage 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 Sage MCP. 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 Sage MCP server (sagemcp/sagemcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 359 Sage MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
359 Sage MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.