更新任务配置
AI agents use cron_update 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.
The tool modifies scheduled task configurations, which is a Write operation. Severity is high because misuse could alter critical scheduled tasks (enabling malicious jobs, disabling security tasks, modifying task parameters), affecting system reliability and security, though changes remain reversible through cron_update again or deletion.
From the tool's definition Tool name 'cron_update' and description '更新任务配置' (update task configuration) indicate modification of existing scheduled task data. This is a reversible data modification operation on cron job configurations.
Attacks that exploit this kind of access
更新任务配置. 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_update: 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_update 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_update 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_update. 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_update 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 →