mail_send · Outpost MCP: Risk & Policy

WHAT IT DOES

What mail_send does on Outpost

AI agents use mail_send to create or update resources in Outpost — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Outpost environment.

WHY IT NEEDS A POLICY

Why mail_send needs a policy

Sending email creates new persistent data (messages in sent folder, receipt by recipients) and can have real-world consequences if misused by an AI agent (spam, impersonation, disclosure of sensitive information, phishing). However, it is reversible (emails can be deleted/recalled in some cases) and does not involve financial transactions, code execution, or irreversible destruction.

From the tool's definition Tool name 'mail_send' and description 'Send an email via Outlook' directly indicate creation of new email messages. This is a write operation that modifies the user's mailbox and communication state.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mail_send Rate-limited

mail_send 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "mail_send": {
      "limits": [
        {
          "counter": "mail_send_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Outpost, so you can run agents against it safely.

FAQ

Questions about mail_send

What does the mail_send tool do? +

Send an email via Outlook. It is categorised as a Write tool in the Outpost MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on mail_send? +

Register the Outpost MCP server in PolicyLayer and add a rule for mail_send: 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 Outpost. Nothing to install.

What risk level is mail_send? +

mail_send is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit mail_send? +

Yes. Add a rate_limit block to the mail_send 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.

How do I block mail_send completely? +

Set action: deny in the PolicyLayer policy for mail_send. 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.

What MCP server provides mail_send? +

mail_send is provided by the Outpost MCP server (signalclaude/outpost). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.