AI agents call search_events to retrieve information from Calendar without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Search operations retrieve or query data without modifying calendar state. The tool name contains 'search', which is characteristic of Read category operations. Sibling tools like 'get_events' and 'list_calendars' are clearly Read operations, and 'search_events' aligns with that usage pattern.
From the tool's definition Tool name 'search_events' indicates a search/query operation. Server description lists 'listing' as a read operation, and 'search_events' fits this pattern. No description provided for the tool itself, lowering confidence slightly.
Attacks that exploit this kind of access
search_events. It is categorised as a Read tool in the Calendar MCP Server, which means it retrieves data without modifying state.
Register the Calendar MCP server in PolicyLayer and add a rule for search_events: 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 Calendar. Nothing to install.
search_events 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 search_events 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 search_events. 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.
search_events is provided by the Calendar MCP server (p-w-4-z/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 →