AI agents use fix-event-times to create or update resources in macOS Calendar MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your macOS Calendar MCP Server environment.
This tool modifies existing calendar events by updating their time fields (correcting midnight times to proper times). This is a Write operation — it updates data reversibly (the event still exists, just with changed times). Severity is medium because an AI agent misusing this could silently alter scheduled events across a calendar, causing missed appointments or scheduling conflicts.
From the tool's definition 修正错误的事件时间（从凌晨修正到正确时间） — 'fix/修正' implies correcting/updating existing event times
Documented attack patterns abuse exactly the kind of access fix-event-times gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and macOS Calendar MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for fix-event-times:
{
"version": "1",
"default": "deny",
"tools": {
"fix-event-times": {
"limits": [
{
"counter": "fix-event-times_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}fix-event-times stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
修正错误的事件时间（从凌晨修正到正确时间）. It is categorised as a Write tool in the macOS Calendar MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the macOS Calendar MCP Server MCP server in PolicyLayer and add a rule for fix-event-times: 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 macOS Calendar MCP Server. Nothing to install.
fix-event-times is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the fix-event-times 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 fix-event-times. 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.
fix-event-times is provided by the macOS Calendar MCP Server MCP server (xybstone/macos-calendar-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from macOS Calendar MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
8 macOS Calendar MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.