AI agents call getRecentMessages to retrieve information from Outlook without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical email data without modifying it. While email can contain sensitive information, the read-only nature and passive data retrieval operation places it in the Read category. Severity is low because it affects only data visibility, not integrity or availability, and the blast radius of accidental misuse is limited to viewing messages the authenticated user already has access to.
From the tool's definition Tool name 'getRecentMessages' and sibling context indicate retrieval of email messages from Outlook. No parameters described for modification, deletion, or external execution.
Attacks that exploit this kind of access
getRecentMessages. It is categorised as a Read tool in the Outlook MCP Server, which means it retrieves data without modifying state.
Register the Outlook MCP server in PolicyLayer and add a rule for getRecentMessages: 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 Outlook. Nothing to install.
getRecentMessages 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 getRecentMessages 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 getRecentMessages. 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.
getRecentMessages is provided by the Outlook MCP server (lihaokun/outlook-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 →