calendar_search
AI agents call calendar_search to retrieve information from Google Calendar MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Calendar search retrieves and queries calendar data without modifying or deleting anything. While the description is empty (lowering confidence slightly), the tool name combined with the server's stated functionality ('search agendas') and the presence of clearly non-destructive sibling tools indicates this is a retrieval operation.
From the tool's definition Tool name 'calendar_search' and server context indicates searching/querying calendar data. Sibling tools include 'calendar_list_events', 'calendar_get_event', 'calendar_daily_agenda', and 'calendar_weekly_summary' which are all Read operations.
Attacks that exploit this kind of access
calendar_search. It is categorised as a Read tool in the Google Calendar MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Google Calendar MCP Server MCP server in PolicyLayer and add a rule for calendar_search: 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 Server. Nothing to install.
calendar_search 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 calendar_search 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 calendar_search. 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.
calendar_search is provided by the Google Calendar MCP Server MCP server (murphy360/mcp_google_calendar). 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 →