mark_all_notifications_read · Payoza MCP Server MCP

WHAT IT DOES

What mark_all_notifications_read does on Payoza MCP Server

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

WHY IT NEEDS A POLICY

Why mark_all_notifications_read needs a policy

This tool modifies notification metadata by changing read status, which is a reversible state change. It does not delete data, execute code, move funds, or perform irreversible actions. It is categorized as Write rather than Read because it actively changes state rather than merely retrieving information.

From the tool's definition Tool name 'mark_all_notifications_read' and description 'Mark all notifications as read' indicate modification of notification state. The operation updates records reversibly (notifications can be marked unread again).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mark_all_notifications_read Rate-limited

mark_all_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_all_notifications_read": {
      "limits": [
        {
          "counter": "mark_all_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 Payoza MCP Server, so you can run agents against it safely.

FAQ

Questions about mark_all_notifications_read

What does the mark_all_notifications_read tool do? +

Mark all notifications as read. It is categorised as a Write tool in the Payoza 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_all_notifications_read? +

Register the Payoza MCP Server MCP server in PolicyLayer and add a rule for mark_all_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 Payoza MCP Server. Nothing to install.

What risk level is mark_all_notifications_read? +

mark_all_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_all_notifications_read? +

Yes. Add a rate_limit block to the mark_all_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_all_notifications_read completely? +

Set action: deny in the PolicyLayer policy for mark_all_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_all_notifications_read? +

mark_all_notifications_read is provided by the Payoza MCP Server MCP server (payoza/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.