read_notification · Habitca MCP: Risk & Policy

WHAT IT DOES

What read_notification does on Habitca

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

WHY IT NEEDS A POLICY

Why read_notification needs a policy

Marking a notification as read modifies its state (read/unread) in the system. This is a reversible write operation with minimal blast radius — it changes notification state but does not delete data or have financial/destructive consequences.

From the tool's definition Mark a notification as read

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

read_notification Rate-limited

read_notification 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": {
    "read_notification": {
      "limits": [
        {
          "counter": "read_notification_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 Habitca, so you can run agents against it safely.

FAQ

Questions about read_notification

What does the read_notification tool do? +

Mark a notification as read. It is categorised as a Write tool in the Habitca MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on read_notification? +

Register the Habitca MCP server in PolicyLayer and add a rule for read_notification: 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 Habitca. Nothing to install.

What risk level is read_notification? +

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

Can I rate-limit read_notification? +

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

Set action: deny in the PolicyLayer policy for read_notification. 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 read_notification? +

read_notification is provided by the Habitca MCP server (leon-jarvis1/habitca_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.