mark_gmail_read · Google Connections MCP: Risk & Policy

WHAT IT DOES

What mark_gmail_read does on Google Connections

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

WHY IT NEEDS A POLICY

Why mark_gmail_read needs a policy

The tool modifies email metadata (read/unread flag) but does not create, delete, or execute code. It is reversible—emails can be marked unread again. This is a Write category action with low severity because it has minimal blast radius; marking emails as read causes no data loss, financial impact, or execution of external operations. Confidence is high because the name and description are explicit and unambiguous.

From the tool's definition Tool name 'mark_gmail_read' and description 'Mark one or more Gmail messages as read' indicate modification of message state/metadata. This is a reversible write operation that changes the read status of emails.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mark_gmail_read Rate-limited

mark_gmail_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_gmail_read": {
      "limits": [
        {
          "counter": "mark_gmail_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 Google Connections, so you can run agents against it safely.

FAQ

Questions about mark_gmail_read

What does the mark_gmail_read tool do? +

Mark one or more Gmail messages as read. It is categorised as a Write tool in the Google Connections 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_gmail_read? +

Register the Google Connections MCP server in PolicyLayer and add a rule for mark_gmail_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 Google Connections. Nothing to install.

What risk level is mark_gmail_read? +

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

Can I rate-limit mark_gmail_read? +

Yes. Add a rate_limit block to the mark_gmail_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_gmail_read completely? +

Set action: deny in the PolicyLayer policy for mark_gmail_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_gmail_read? +

mark_gmail_read is provided by the Google Connections MCP server (michaelzrork/google-connections-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.