Book a meeting on another user's public calendar by their Temporal Link slug. Requires attendee_email. Content sanitization and Two-Phase Commit happen server-side. If the slot is taken, returns a 409 Conflict error — query availability again. Requires Platform Mode.
AI agents call request_booking to retrieve information from Temporal Cortex Calendar MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
end | string | Yes | End time for the booking (RFC 3339 datetime string). |
slug | string | Yes | Temporal Link slug (e.g., "jane-doe"). |
start | string | Yes | Start time for the booking (RFC 3339 datetime string). |
title | string | Yes | Meeting title. |
description | string | null | — | Optional meeting description. |
attendee_name | string | null | — | Your display name (optional). |
attendee_email | string | Yes | Your email address (required for the calendar invitation). |
Parameters from the server's own tool schema.
Even though request_booking only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
Book a meeting on another user's public calendar by their Temporal Link slug. Requires attendee_email. Content sanitization and Two-Phase Commit happen server-side. If the slot is taken, returns a 409 Conflict error — query availability again. Requires Platform Mode. It is categorised as a Read tool in the Temporal Cortex Calendar MCP MCP Server, which means it retrieves data without modifying state.
request_booking accepts 7 parameters: end, slug, start, title, description, attendee_name, attendee_email. Required: end, slug, start, title, attendee_email. The full parameter table on this page comes from the server's own tool schema.
Register the Temporal Cortex Calendar MCP server in PolicyLayer and add a rule for request_booking: 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 Temporal Cortex Calendar MCP. Nothing to install.
request_booking 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 request_booking 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 request_booking. 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.
request_booking is provided by the Temporal Cortex Calendar MCP server (temporal-cortex/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.