AI agents call getMessage 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 and queries existing email message content without modifying, deleting, or executing any operations. It is purely informational in nature, consistent with the 'Read' category for tools that retrieve data with no side effects. The low severity reflects that reading email messages, while potentially sensitive depending on content, does not cause irreversible changes or trigger external actions.
From the tool's definition Tool name is 'getMessage' and description states 'Read full message content including body and attachments.' The verb 'Read' and the retrieval-only nature (no modifications, deletions, or side effects) clearly indicate this is a data retrieval operation.
Attacks that exploit this kind of access
Read full message content including body and attachments. 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 getMessage: 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.
getMessage 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 getMessage 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 getMessage. 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.
getMessage 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 →