email_mark_read · M365 MCP: Risk & Policy

WHAT IT DOES

What email_mark_read does on M365

AI agents use email_mark_read to create or update resources in M365 — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your M365 environment.

WHY IT NEEDS A POLICY

Why email_mark_read needs a policy

This tool modifies email metadata (read status) but the operation is reversible—emails can be marked unread again. It does not delete, execute code, move money, or trigger external operations with unpredictable side effects. The empty description lowers confidence slightly, but the function name is clear enough to classify as a Write operation.

From the tool's definition Tool name 'email_mark_read' indicates modification of email message state. The server context describes managing Microsoft 365 Outlook services. Marking emails as read is a reversible state change operation.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

email_mark_read Rate-limited

email_mark_read 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": {
    "email_mark_read": {
      "limits": [
        {
          "counter": "email_mark_read_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 M365, so you can run agents against it safely.

FAQ

Questions about email_mark_read

What does the email_mark_read tool do? +

email_mark_read. It is categorised as a Write tool in the M365 MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on email_mark_read? +

Register the M365 MCP server in PolicyLayer and add a rule for email_mark_read: 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 M365. Nothing to install.

What risk level is email_mark_read? +

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

Can I rate-limit email_mark_read? +

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

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

email_mark_read is provided by the M365 MCP server (robin-collins/m365-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.