gmail_mark_read · Personal Gmail MCP: Risk & Policy

WHAT IT DOES

What gmail_mark_read does on Personal Gmail

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

WHY IT NEEDS A POLICY

Why gmail_mark_read needs a policy

This tool modifies message metadata (the UNREAD flag) in Gmail, changing the read/unread state of emails. This is a reversible write operation—the state can be toggled back. It does not retrieve data (Read), execute external commands (Execute), permanently delete data (Destructive), or involve financial transactions (Financial).

From the tool's definition Tool description states it can 'Mark a message read (remove UNREAD) or unread (add UNREAD)', indicating modification of message state/metadata.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

gmail_mark_read Rate-limited

gmail_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": {
    "gmail_mark_read": {
      "limits": [
        {
          "counter": "gmail_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 Personal Gmail, so you can run agents against it safely.

FAQ

Questions about gmail_mark_read

What does the gmail_mark_read tool do? +

Mark a message read (remove UNREAD) or unread (add UNREAD). Pass isRead=false to mark unread. It is categorised as a Write tool in the Personal 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 gmail_mark_read? +

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

What risk level is gmail_mark_read? +

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

Can I rate-limit gmail_mark_read? +

Yes. Add a rate_limit block to the gmail_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 gmail_mark_read completely? +

Set action: deny in the PolicyLayer policy for gmail_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 gmail_mark_read? +

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