AI agents call upcoming to retrieve information from Calendar without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves calendar event data for a specified future time window. It is a read-only query operation that has no side effects on the calendar state or external systems. Even in a calendar context where other sibling tools include destructive operations (delete_event) and write operations (create_event, update_event), this specific tool only fetches data.
From the tool's definition Tool name 'upcoming' and description 'Get upcoming events in the next N hours' indicates a retrieval operation with no side effects. It queries calendar data without modifying, deleting, or executing external operations.
Attacks that exploit this kind of access
Get upcoming events in the next N hours. It is categorised as a Read tool in the Calendar MCP Server, which means it retrieves data without modifying state.
Register the Calendar MCP server in PolicyLayer and add a rule for upcoming: 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.
upcoming is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the upcoming 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 upcoming. 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.
upcoming 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 →