Get full email details including body (HTML auto-converted to plain text), CC/BCC recipients, and attachment metadata. Body is included by default. The message_id MUST be the exact id from a recent mail_list_messages call. For your own mailbox, OMIT the mailbox parameter (it defaults to you); onl...
AI agents call mail_get_message to retrieve information from M365 without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs read-only operations on email data. It retrieves message content and metadata without side effects. The requirement to use a message_id from mail_list_messages and the ability to access shared mailboxes are authorization/access control mechanisms, not functional capabilities that elevate the risk beyond data retrieval.
From the tool's definition Tool retrieves and queries email message details including body, recipients, and attachment metadata. The description explicitly states it 'Get[s] full email details' and 'To read an attachment, call mail_get_attachment'—indicating this tool only retrieves…
Attacks that exploit this kind of access
Get full email details including body (HTML auto-converted to plain text), CC/BCC recipients, and attachment metadata. Body is included by default. The message_id MUST be the exact id from a recent mail_list_messages call. For your own mailbox, OMIT the mailbox parameter (it defaults to you); only set mailbox to a shared mailbox email address when the listed messages came from one. To read an attachment, call mail_get_attachment with the same message_id. It is categorised as a Read tool in the M365 MCP Server, which means it retrieves data without modifying state.
Register the M365 MCP server in PolicyLayer and add a rule for mail_get_message: 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 M365. Nothing to install.
mail_get_message 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 mail_get_message 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 mail_get_message. 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.
mail_get_message is provided by the M365 MCP server (swamirama/m365-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 →