AI agents use create_event to create or update resources in Calendar — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Calendar environment.
Creating calendar events is a reversible write operation — events can be modified or deleted later. It modifies user calendar state but is not destructive (deletion tools exist separately). Severity is medium: an agent creating spurious/malicious calendar events could clutter calendars or cause scheduling conflicts, but the impact is containable and reversible.
From the tool's definition Tool name is 'create_event' on a calendar MCP server. Server description explicitly lists 'creating...events' as a capability. Sibling tools include 'delete_event' and 'update_event', confirming write/modification operations.
Attacks that exploit this kind of access
create_event. It is categorised as a Write tool in the Calendar MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Calendar MCP server in PolicyLayer and add a rule for create_event: 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 Calendar. Nothing to install.
create_event 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 create_event 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 create_event. 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.
create_event is provided by the Calendar MCP server (p-w-4-z/calendar-mcp). 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 →