mark_read · Inbox MCP: Risk & Policy

WHAT IT DOES

What mark_read does on Inbox

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

WHY IT NEEDS A POLICY

Why mark_read needs a policy

This tool modifies email message state (marking as read) but the change is reversible (messages can be marked unread). It affects only metadata, not data content or deletion. Severity is medium because marking many messages as read could obscure important unread emails and disrupt user workflows, but the action is not destructive or irreversible.

From the tool's definition Tool sets the IMAP Seen flag on messages, which modifies message state. Name 'mark_read' and description 'sets the IMAP Seen flag' indicate a write operation that changes message metadata.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mark_read Rate-limited

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": {
    "mark_read": {
      "limits": [
        {
          "counter": "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 Inbox, so you can run agents against it safely.

FAQ

Questions about mark_read

What does the mark_read tool do? +

Mark one or more messages as read (sets the IMAP Seen flag). It is categorised as a Write tool in the Inbox 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_read? +

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

What risk level is mark_read? +

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

Can I rate-limit mark_read? +

Yes. Add a rate_limit block to the 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 mark_read completely? +

Set action: deny in the PolicyLayer policy for 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 mark_read? +

mark_read is provided by the Inbox MCP server (p-w-4-z/inbox-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.