flag-email · Outlook MCP Server MCP: Risk & Policy

WHAT IT DOES

What flag-email does on Outlook MCP Server

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

WHY IT NEEDS A POLICY

Why flag-email needs a policy

This tool modifies metadata on an existing email (its flag/follow-up status and associated dates). This is a reversible write operation — flags can be set and unset — with no code execution, deletion, or financial impact. Misuse could affect email triage workflows but is limited in blast radius.

From the tool's definition Sets the flag status on an email. Can optionally set start and due dates for follow-up.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

flag-email Rate-limited

flag-email 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": {
    "flag-email": {
      "limits": [
        {
          "counter": "flag-email_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 MCP Server, so you can run agents against it safely.

FAQ

Questions about flag-email

What does the flag-email tool do? +

Sets the flag status on an email. Can optionally set start and due dates for follow-up. It is categorised as a Write tool in the Outlook MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on flag-email? +

Register the Outlook MCP Server MCP server in PolicyLayer and add a rule for flag-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 Outlook MCP Server. Nothing to install.

What risk level is flag-email? +

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

Can I rate-limit flag-email? +

Yes. Add a rate_limit block to the flag-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.

How do I block flag-email completely? +

Set action: deny in the PolicyLayer policy for flag-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.

What MCP server provides flag-email? +

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