sendMail · Outlook MCP: Risk & Policy

WHAT IT DOES

What sendMail does on Outlook

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

WHY IT NEEDS A POLICY

Why sendMail needs a policy

sendMail creates and transmits new email messages, which is a reversible Write operation. Severity is high because unsupervised email sending by an AI agent could result in unauthorized communications, impersonation, phishing, or reputation damage, though no financial or destructive data loss occurs.

From the tool's definition Tool name 'sendMail' combined with context of Outlook MCP server that 'enables AI assistants to access email, contacts, and calendars.' Sibling tools include 'replyToMessage', 'forwardMessage', and 'getMessage', establishing this as an email operation tool.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

sendMail Rate-limited

sendMail 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": {
    "sendMail": {
      "limits": [
        {
          "counter": "sendmail_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 Outlook, so you can run agents against it safely.

FAQ

Questions about sendMail

What does the sendMail tool do? +

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

How do I enforce a policy on sendMail? +

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

What risk level is sendMail? +

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

Can I rate-limit sendMail? +

Yes. Add a rate_limit block to the sendMail 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 sendMail completely? +

Set action: deny in the PolicyLayer policy for sendMail. 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 sendMail? +

sendMail is provided by the Outlook MCP server (lihaokun/outlook-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.