AI agents use create_calendar to create or update resources in Mcp Ical — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Ical environment.
Creating calendar files is a Write operation because it generates and structures data that can be modified or deleted later. Severity is medium because misuse could create spam calendar events or inject malicious calendar data into systems, but the impact is limited to calendar data rather than system-wide or financial consequences.
From the tool's definition Tool description states 'Build a multi-event ICS calendar file' — this creates new calendar data structures. The verb 'build' indicates data generation/creation, which is a Write operation.
Attacks that exploit this kind of access
Build a multi-event ICS calendar file from an array of events. It is categorised as a Write tool in the Mcp Ical MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Ical MCP server in PolicyLayer and add a rule for 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 Mcp Ical. Nothing to install.
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 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 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.
create_calendar is provided by the Mcp Ical MCP server (jeffereychown-max/mcp-ical). 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 →