AI agents call query_freebusy to retrieve information from Gcalendar without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves scheduling information (free/busy status) from Google Calendar. It has no side effects, does not create, modify, or delete data, and does not execute external operations. It is purely informational retrieval, fitting the 'Read' category. Severity is low because misuse would at worst leak availability information, not cause operational harm.
From the tool's definition Tool name 'query_freebusy' and description 'Query free/busy information' indicate a retrieval operation. The verb 'query' combined with 'free/busy information' (availability data) shows this retrieves calendar availability without modifying or executing…
Attacks that exploit this kind of access
Query free/busy information. It is categorised as a Read tool in the Gcalendar MCP Server, which means it retrieves data without modifying state.
Register the Gcalendar MCP server in PolicyLayer and add a rule for query_freebusy: 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 Gcalendar. Nothing to install.
query_freebusy 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 query_freebusy 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 query_freebusy. 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.
query_freebusy is provided by the Gcalendar MCP server (sandeepmallareddy/gcalendar-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 →