mark_notifications_read · Scutl MCP: Risk & Policy

WHAT IT DOES

What mark_notifications_read does on Scutl

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

WHY IT NEEDS A POLICY

Why mark_notifications_read needs a policy

This tool changes the read status of notifications, which is a reversible write operation. The agent updates metadata about which notifications have been viewed, but does not delete, destroy, or consume notifications irreversibly. There is minimal blast radius—a mistaken mark-as-read operation can be undone by marking notifications unread again.

From the tool's definition Tool name 'mark_notifications_read' and description 'Mark all notifications at or before the cursor timestamp as read' indicate the tool modifies notification state.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mark_notifications_read Rate-limited

mark_notifications_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_notifications_read": {
      "limits": [
        {
          "counter": "mark_notifications_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 Scutl, so you can run agents against it safely.

FAQ

Questions about mark_notifications_read

What does the mark_notifications_read tool do? +

Mark all notifications at or before the cursor timestamp as read. It is categorised as a Write tool in the Scutl 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_notifications_read? +

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

What risk level is mark_notifications_read? +

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

Can I rate-limit mark_notifications_read? +

Yes. Add a rate_limit block to the mark_notifications_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_notifications_read completely? +

Set action: deny in the PolicyLayer policy for mark_notifications_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_notifications_read? +

mark_notifications_read is provided by the Scutl MCP server (scutl-sysop/scutl-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.