AI agents use cron_task_done to create or update resources in Tools — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tools environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
status | string | — | Execution result (default: "success"). Use "failed" to trigger retry if max_retries is set. |
message | string | — | Optional message about the result (e.g. error details) |
task_id | string | Yes | Task ID to mark as done |
agent_id | string | — | Your agent identifier (default: "default") |
Parameters from the server's own tool schema.
This tool modifies the state of an existing scheduled task (marking it complete/failed) but does not delete or irreversibly destroy data. The operation is reversible—a task can be re-run or its state can be changed again. This places it in the Write category rather than Destructive.
From the tool's definition Tool description states 'Mark a scheduled task as completed or failed', indicating modification of task state. The mention of 'failure tracking and auto-retry' suggests reversible state changes to existing cron tasks rather than irreversible deletion.
Attacks that exploit this kind of access
Mark a scheduled task as completed or failed. Supports failure tracking and auto-retry. It is categorised as a Write tool in the Tools MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
cron_task_done accepts 4 parameters: status, message, task_id, agent_id. Required: task_id. The full parameter table on this page comes from the server's own tool schema.
Register the Tools MCP server in PolicyLayer and add a rule for cron_task_done: 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 Tools. Nothing to install.
cron_task_done 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_task_done 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_task_done. 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_task_done is provided by the Tools MCP server (https://www.jiebang.site/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 →