添加定时任务。支持三种调度类型:at(一次性)、every(间隔)、cron(表达式)。Cron 表达式会在创建前进行语法验证。
AI agents use cron_add to create or update resources in MCP Cron Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Cron Server environment.
This tool creates a new scheduled task in the system. Creating a scheduled task is a Write operation (reversible via cron_remove). However, severity is high because a misused scheduled task could trigger repeated arbitrary executions, cause resource exhaustion, or schedule destructive operations — amplifying any downstream harm through automation.
From the tool's definition 添加定时任务 (Add scheduled task) — creates a new cron job/scheduled task
Attacks that exploit this kind of access
添加定时任务。支持三种调度类型:at(一次性)、every(间隔)、cron(表达式)。Cron 表达式会在创建前进行语法验证。. It is categorised as a Write tool in the MCP Cron Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Cron Server MCP server in PolicyLayer and add a rule for cron_add: 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 Cron Server. Nothing to install.
cron_add 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 cron_add 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 cron_add. 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.
cron_add is provided by the MCP Cron Server MCP server (nolan57/opencode-mcp-cron). 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 →