AI agents call suggest_schedule to retrieve information from Gcal without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool only reads existing calendar data (tasks, energy levels, free slots) and returns a suggested schedule as output. It explicitly states it does not book or modify anything, making it a pure read/query operation with no side effects.
From the tool's definition 'Propose an optimized schedule' and 'Does NOT book anything — returns a proposal for you to review and approve'
Attacks that exploit this kind of access
Propose an optimized schedule for a given date based on task priorities, energy levels, and free calendar slots. Does NOT book anything — returns a proposal for you to review and approve. It is categorised as a Read tool in the Gcal MCP Server, which means it retrieves data without modifying state.
Register the Gcal MCP server in PolicyLayer and add a rule for suggest_schedule: 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.
suggest_schedule 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 suggest_schedule 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 suggest_schedule. 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.
suggest_schedule 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 →