ms365_send_email
AI agents use ms365_send_email to create or update resources in Microsoft 365 MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Microsoft 365 MCP Server environment.
Sending an email creates and transmits a message that modifies the user's mailbox state and reaches external recipients. This is a Write operation—data is created and committed (though reversible through deletion/recall mechanisms). It carries high severity because a misdirected or malicious email could damage professional relationships, leak sensitive information, or constitute impersonation.
From the tool's definition Tool name 'ms365_send_email' combined with server description stating the tool enables users to 'manage emails...via the Microsoft Graph API'.
Attacks that exploit this kind of access
ms365_send_email. It is categorised as a Write tool in the Microsoft 365 MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Microsoft 365 MCP Server MCP server in PolicyLayer and add a rule for ms365_send_email: 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 365 MCP Server. Nothing to install.
ms365_send_email is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the ms365_send_email 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 ms365_send_email. 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.
ms365_send_email is provided by the Microsoft 365 MCP Server MCP server (ronaldzuniga/ms365-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 →