Reply to a mail message. Sends immediately to the original sender. Thread preservation: the original message is automatically appended below your reply, with its original HTML formatting (signatures, inline images, prior quoted thread) intact - exactly the way clicking
AI agents use reply-mail to create or update resources in Outlook OAuth MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Outlook OAuth MCP Server environment.
This tool creates and sends email messages, which is a reversible write operation (emails can be deleted but the send action itself is committed). It does not execute arbitrary code, delete data irreversibly, or move money.
From the tool's definition Tool name is 'reply-mail' and description states it 'Sends immediately to the original sender.' This creates a new message (write operation) and commits it to send, modifying the user's sent items and the recipient's inbox.
Attacks that exploit this kind of access
Reply to a mail message. Sends immediately to the original sender. Thread preservation: the original message is automatically appended below your reply, with its original HTML formatting (signatures, inline images, prior quoted thread) intact - exactly the way clicking. It is categorised as a Write tool in the Outlook OAuth MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Outlook OAuth MCP Server MCP server in PolicyLayer and add a rule for reply-mail: 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 OAuth MCP Server. Nothing to install.
reply-mail 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 reply-mail 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 reply-mail. 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.
reply-mail is provided by the Outlook OAuth MCP Server MCP server (leonine-studios/useful-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 →