mark_notification_read · HC3 MCP Server MCP: Risk & Policy

WHAT IT DOES

What mark_notification_read does on HC3 MCP Server

AI agents use mark_notification_read to create or update resources in HC3 MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your HC3 MCP Server environment.

WHY IT NEEDS A POLICY

Why mark_notification_read needs a policy

This tool modifies the read status of a notification, which is a reversible state change. It does not create, retrieve, execute commands, delete data irreversibly, or involve financial operations. The blast radius is minimal—marking a notification as read has no cascading effects on the smart home system's critical functions (devices, scenes, alarms, backups) and is easily reversed by marking it unread.

From the tool's definition Tool name 'mark_notification_read' and description 'Mark notification as read' indicate modification of notification state/metadata.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mark_notification_read Rate-limited

mark_notification_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_notification_read": {
      "limits": [
        {
          "counter": "mark_notification_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 HC3 MCP Server, so you can run agents against it safely.

FAQ

Questions about mark_notification_read

What does the mark_notification_read tool do? +

Mark notification as read. It is categorised as a Write tool in the HC3 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_notification_read? +

Register the HC3 MCP Server MCP server in PolicyLayer and add a rule for mark_notification_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 HC3 MCP Server. Nothing to install.

What risk level is mark_notification_read? +

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

Can I rate-limit mark_notification_read? +

Yes. Add a rate_limit block to the mark_notification_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_notification_read completely? +

Set action: deny in the PolicyLayer policy for mark_notification_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_notification_read? +

mark_notification_read is provided by the HC3 MCP Server MCP server (jangabrielsson/hc3_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.