mark_message_read

THE RISK

Medium Risk

Why mark_message_read needs a policy

This tool modifies message metadata (read/unread status) rather than reading data or executing arbitrary operations. The change is reversible (messages can be marked unread again), and the blast radius is limited to email metadata state. It does not delete data, access sensitive content beyond what the user already has access to, or trigger external operations.

From the tool's definition Tool marks a message as read by removing the UNREAD label, which modifies the state/metadata of an existing message. The description explicitly states an action that changes data: 'removing the UNREAD label'.

Documented attack patterns abuse exactly the kind of access mark_message_read gives an agent:

POLICY

How to control mark_message_read

PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Gmail, and nothing reaches the server without passing your rules. This is the rule we recommend for mark_message_read:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "mark_message_read": {
      "limits": [
        {
          "counter": "mark_message_read_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

mark_message_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.

Create a free account and register Mcp Gmail — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Mcp Gmail tools

Write remove_label_from_message Remove a label from a message. Write compose_email compose_email Write add_label_to_message Add a label to a message. Write send_email Compose and send an email. Read get_emails Get the content of multiple email messages by their IDs. Read list_available_labels Get all available Gmail labels for the user. Read query_emails Search for emails using a raw Gmail query string. Read search_emails search_emails

All 9 Mcp Gmail tools →

Write tools on other servers

M-Team MCP Server download_torrent YouTube MCP Server generate_video_title Android Forensics ADB MCP Server combine_reports 0xarchive web3_signup

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Argument validation → Checking tool call arguments against schema and policy before they run.
Scoped token → Per-person credentials that grant a defined subset of servers and tools.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about mark_message_read

What does the mark_message_read tool do? +

Mark a message as read by removing the UNREAD label. It is categorised as a Write tool in the Mcp 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_message_read? +

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

What risk level is mark_message_read? +

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

Can I rate-limit mark_message_read? +

Yes. Add a rate_limit block to the mark_message_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_message_read completely? +

Set action: deny in the PolicyLayer policy for mark_message_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_message_read? +

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

Enforce policy on every Mcp Gmail tool call.

Start from Mcp Gmail, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →