AI agents use calendar_create_calendar to create or update resources in Google — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Google environment.
Creating a calendar is a Write operation—it produces a new, reversible resource. The user can delete or modify the calendar afterward. Severity is medium because while calendar creation itself is low-risk, it could facilitate subsequent misuse (e.g., an AI agent creates calendars to spam invites or distribute misinformation through shared calendars).
From the tool's definition Tool name 'calendar_create_calendar' and description 'Create a new calendar' indicate creation of a new resource in Google Calendar.
Attacks that exploit this kind of access
Create a new calendar. It is categorised as a Write tool in the Google MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Google MCP server in PolicyLayer and add a rule for calendar_create_calendar: 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 Google. Nothing to install.
calendar_create_calendar 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 calendar_create_calendar 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 calendar_create_calendar. 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.
calendar_create_calendar is provided by the Google MCP server (robcerda/google-mcp-server). 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 →