mark_email · Gmail MCP: Risk & Policy

WHAT IT DOES

What mark_email does on Gmail

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

WHY IT NEEDS A POLICY

Why mark_email needs a policy

This tool modifies email attributes (read status, star status, importance flag) but does not create, delete, or send data. All changes are reversible—emails can be unmarked, unstarred, or marked as unimportant. It falls under Write category (reversible modification). Severity is low because the blast radius is confined to email metadata flags with no data loss, financial impact, or code execution risk.

From the tool's definition Tool description states it can 'Mark an email as read/unread, starred/unstarred, or important/unimportant' - these are reversible modifications to email metadata/flags.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mark_email Rate-limited

mark_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": {
    "mark_email": {
      "limits": [
        {
          "counter": "mark_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 Gmail, so you can run agents against it safely.

FAQ

Questions about mark_email

What does the mark_email tool do? +

Mark an email as read/unread, starred/unstarred, or important/unimportant. It is categorised as a Write tool in the Gmail 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_email? +

Register the Gmail MCP server in PolicyLayer and add a rule for mark_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 Gmail. Nothing to install.

What risk level is mark_email? +

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

Can I rate-limit mark_email? +

Yes. Add a rate_limit block to the mark_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 mark_email completely? +

Set action: deny in the PolicyLayer policy for mark_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 mark_email? +

mark_email is provided by the Gmail MCP server (ndungukamami-sketch/gmail-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.