Record a notification in the DB (after Calendar event was successfully created).
AI agents use record_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.
This tool writes/records a notification entry into a SQLite database. It creates a new record but does not delete or overwrite existing data, execute arbitrary code, or involve financial transactions. The operation appears to be a simple persistence step following a calendar event creation, making it a reversible write action with low blast radius.
From the tool's definition Record a notification in the DB (after Calendar event was successfully created).
Attacks that exploit this kind of access
Record a notification in the DB (after Calendar event was successfully created). 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.
Register the Claude Sync MCP server in PolicyLayer and add a rule for record_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.
record_notification is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the record_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.
Set action: deny in the PolicyLayer policy for record_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.
record_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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →