prepare_notification · Claude Sync MCP: Risk & Policy

WHAT IT DOES

What prepare_notification does on Claude Sync

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

WHY IT NEEDS A POLICY

Why prepare_notification needs a policy

The tool prepares/builds calendar event parameters, which implies constructing or creating data structures for a notification event. This is a Write operation as it creates new data. However, 'prepare' and 'build parameters' could also imply it's just formatting data without persisting it, which would lower severity.

From the tool's definition Build Calendar event parameters for a notification

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

prepare_notification Rate-limited

prepare_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": {
    "prepare_notification": {
      "limits": [
        {
          "counter": "prepare_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 Claude Sync, so you can run agents against it safely.

FAQ

Questions about prepare_notification

What does the prepare_notification tool do? +

Build Calendar event parameters for a notification. It is categorised as a Write tool in the Claude Sync MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on prepare_notification? +

Register the Claude Sync MCP server in PolicyLayer and add a rule for prepare_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 Claude Sync. Nothing to install.

What risk level is prepare_notification? +

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

Can I rate-limit prepare_notification? +

Yes. Add a rate_limit block to the prepare_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 prepare_notification completely? +

Set action: deny in the PolicyLayer policy for prepare_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 prepare_notification? +

prepare_notification is provided by the Claude Sync MCP server (the-firmament/claude-sync). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.