カレンダー予定の詳細を取得します
AI agents call get_calendar_event to retrieve information from hokan MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves existing calendar event data without modifying, executing, deleting, or creating anything. It poses minimal security risk as it simply reads information. Severity is low because unauthorized access to calendar details is a read-only information disclosure risk, not a destructive or operational threat.
From the tool's definition get_calendar_event retrieves calendar event details (カレンダー予定の詳細を取得します translates to 'retrieves calendar event details'). The 'get_' prefix and retrieval operation indicate a query/fetch action with no side effects.
Attacks that exploit this kind of access
カレンダー予定の詳細を取得します. It is categorised as a Read tool in the hokan MCP Server MCP Server, which means it retrieves data without modifying state.
Register the hokan MCP Server MCP server in PolicyLayer and add a rule for get_calendar_event: 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 hokan MCP Server. Nothing to install.
get_calendar_event 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_calendar_event 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_calendar_event. 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_calendar_event is provided by the hokan MCP Server MCP server (shinonft/hokan-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 →