AI agents use quick_add_task to create or update resources in Gcal — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Gcal environment.
This tool creates new data (a task) and modifies calendar state by scheduling it, which are reversible write operations. It does not delete data (ruling out Destructive), does not execute arbitrary code (ruling out Execute), and does not involve money (ruling out Financial). While it writes to calendar data, the blast radius is limited to task/calendar entries that can be edited or deleted if needed.
From the tool's definition Tool description states "Create a task and schedule it in one call" - the word "Create" indicates a write operation that modifies calendar and task data by adding new entries.
Attacks that exploit this kind of access
Create a task and schedule it in one call. Combines add_task + schedule_task. Provide task details plus a date/time/timezone for the calendar block. It is categorised as a Write tool in the Gcal MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Gcal MCP server in PolicyLayer and add a rule for quick_add_task: 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 Gcal. Nothing to install.
quick_add_task 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 quick_add_task 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 quick_add_task. 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.
quick_add_task is provided by the Gcal MCP server (kwikkid/gcalcli). 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 →