创建定时任务
AI agents use create_schedule to create or update resources in MCP Reminder Service — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Reminder Service environment.
create_schedule creates and persists new scheduled reminder tasks, which is a reversible modification of data. While it doesn't read data (Read), execute arbitrary code (Execute), or delete data (Destructive), it does create persistent records in the reminder service.
From the tool's definition Tool creates scheduled tasks (cron-based scheduled notifications) that modify system state by adding new reminder schedules to the system.
Attacks that exploit this kind of access
创建定时任务. It is categorised as a Write tool in the MCP Reminder Service MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Reminder Service MCP server in PolicyLayer and add a rule for create_schedule: 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 MCP Reminder Service. Nothing to install.
create_schedule 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 create_schedule 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 create_schedule. 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.
create_schedule is provided by the MCP Reminder Service MCP server (xiaohui/mcp_reminder). 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 →