This record as markdown: /tools/heznpc-airmcp/reply-mail.md
What reply_mail does on AirMCP
AI agents use reply_mail to create or update resources in AirMCP, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AirMCP environment.
Why reply_mail is rated Medium
This tool sends an email reply, which is a write/create operation with external communication side effects. While reversible in principle (emails can sometimes be recalled), sending an email to external parties is a significant action with potential reputational, privacy, and social consequences. It does not delete data, execute code, or move money, so Write is the most appropriate category.
From the tool's definition "Reply to an email message" and "Requires allowSendMail config"
Attacks that exploit this kind of access
The rule that runs reply_mail safely
PolicyLayer is an MCP gateway: it sits between your AI agents and AirMCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For reply_mail, this is the rule to start with:
reply_mail stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect AirMCP, apply this rule, and every reply_mail call is checked against it from then on.
Questions about reply_mail
Reply to an email message. Requires allowSendMail config. It is categorised as a Write tool in the AirMCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Air 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 AirMCP. 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 Air MCP server (airmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Air, and thousands of servers like it.
This server
Across the catalogue