mark_as_read · AGH Mail MCP Server MCP: Risk & Policy

WHAT IT DOES

What mark_as_read does on AGH Mail MCP Server

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

WHY IT NEEDS A POLICY

Why mark_as_read needs a policy

This tool modifies email state (the Seen flag) but does not delete, destroy, or create new data—it only changes a flag on existing emails. The operation is reversible (the flag can be unset). This falls under Write rather than Read since it causes side effects on the mailbox state.

From the tool's definition Tool description states it marks a specific email as read by setting the \Seen flag, which is a reversible modification of email metadata.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mark_as_read Rate-limited

mark_as_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_as_read": {
      "limits": [
        {
          "counter": "mark_as_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 AGH Mail MCP Server, so you can run agents against it safely.

FAQ

Questions about mark_as_read

What does the mark_as_read tool do? +

Oznacza konkretny mail jako przeczytany (ustawia flagę \\Seen). It is categorised as a Write tool in the AGH Mail MCP Server 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_as_read? +

Register the AGH Mail MCP Server MCP server in PolicyLayer and add a rule for mark_as_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 AGH Mail MCP Server. Nothing to install.

What risk level is mark_as_read? +

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

Can I rate-limit mark_as_read? +

Yes. Add a rate_limit block to the mark_as_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_as_read completely? +

Set action: deny in the PolicyLayer policy for mark_as_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_as_read? +

mark_as_read is provided by the AGH Mail MCP Server MCP server (nikodem5/agh-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.