mark_as_read · Email MCP: Risk & Policy

WHAT IT DOES

What mark_as_read does on Email

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

WHY IT NEEDS A POLICY

Why mark_as_read needs a policy

This tool reversibly modifies email properties (read/unread status) without deleting data or causing irreversible changes. It is a Write operation because it alters stored data, but severity is low because the change is easily reversible and has minimal blast radius—changing read status does not expose sensitive data, move money, execute code, or delete anything.

From the tool's definition Tool description states 'Mark an email as read or unread', which modifies email metadata state. The name 'mark_as_read' and description indicate a state change operation on email messages.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mark_as_read Rate-limited

mark_as_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": {
    "mark_as_read": {
      "limits": [
        {
          "counter": "mark_as_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 Email, so you can run agents against it safely.

FAQ

Questions about mark_as_read

What does the mark_as_read tool do? +

Mark an email as read or unread. It is categorised as a Write tool in the Email MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on mark_as_read? +

Register the Email MCP server in PolicyLayer and add a rule for mark_as_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 Email. Nothing to install.

What risk level is mark_as_read? +

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

Can I rate-limit mark_as_read? +

Yes. Add a rate_limit block to the mark_as_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 mark_as_read completely? +

Set action: deny in the PolicyLayer policy for mark_as_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 mark_as_read? +

mark_as_read is provided by the Email MCP server (kerodkibatu/email-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.