Reply to an email message.
AI agents use ms365_reply_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.
Replying to an email is a Write operation that sends a message to external parties. It is reversible in the sense that the email is sent but not destructive or financial. However, the blast radius is high because an AI agent could inadvertently send replies to unintended recipients or with incorrect content, potentially leaking sensitive information or causing reputational harm.
From the tool's definition 'Reply to an email message' — creates a new reply to an existing email, sending it to external recipients
Attacks that exploit this kind of access
Reply to an email message. 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_reply_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_reply_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_reply_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_reply_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_reply_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 →