Check free/busy status for one or more people within a time range
AI agents call get_free_busy to retrieve information from Google Calendar MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves calendar availability data (free/busy status) for specified people and time ranges. It is a read-only query operation with no ability to modify, create, delete, or execute actions. The information returned is non-sensitive aggregate availability status rather than detailed event contents.
From the tool's definition Tool description states 'Check free/busy status' which is a query operation that retrieves availability information without modifying or deleting any data. No side effects or state changes occur.
Attacks that exploit this kind of access
Check free/busy status for one or more people within a time range. It is categorised as a Read tool in the Google Calendar MCP MCP Server, which means it retrieves data without modifying state.
Register the Google Calendar MCP server in PolicyLayer and add a rule for get_free_busy: 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 Google Calendar MCP. Nothing to install.
get_free_busy 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 get_free_busy 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 get_free_busy. 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.
get_free_busy is provided by the Google Calendar MCP server (paytience/google-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 →