control_task
对任务发出协作式控制：action=pause 请求在下一个安全点（下一次页面请求前）暂停，正在提交中的操作不会被强杀；action=resume 把已暂停的任务放回队列（state=queued），不会自动启动执行者，要继续请再调用 run_task，它会从已确认的 next_index 和已保存的页继续，不跳页、不重复记账。重复同样的请求无害（changed=false）；已完成/失败的任务报 task_finished，不存在的报 task_not_found，其他 action 报 invalid_task_action。
This record as markdown: /tools/1point3acres-toolkit/control-task.md
What control_task does on 1point3acres Toolkit
AI agents invoke control_task to trigger actions in 1point3acres Toolkit. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why control_task is rated High
Controls task execution flow by pausing or resuming running automation tasks.
From the tool's definition control_task: pause, resume, run_task, triggers execution flow
Attacks that exploit this kind of access
The rule that runs control_task safely
PolicyLayer is an MCP gateway: it sits between your AI agents and 1point3acres Toolkit, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For control_task, this is the rule to start with:
control_task stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect 1point3acres Toolkit, apply this rule, and every control_task call is checked against it from then on.
Questions about control_task
对任务发出协作式控制：action=pause 请求在下一个安全点（下一次页面请求前）暂停，正在提交中的操作不会被强杀；action=resume 把已暂停的任务放回队列（state=queued），不会自动启动执行者，要继续请再调用 run_task，它会从已确认的 next_index 和已保存的页继续，不跳页、不重复记账。重复同样的请求无害（changed=false）；已完成/失败的任务报 task_finished，不存在的报 task_not_found，其他 action 报 invalid_task_action。. It is categorised as a Execute tool in the 1point3acres Toolkit MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the 1point3acres Toolkit MCP server in PolicyLayer and add a rule for control_task: 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 1point3acres Toolkit. Nothing to install.
control_task is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the control_task 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 control_task. 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.
control_task is provided by the 1point3acres Toolkit MCP server (vivian-labs/1point3acres-toolkit). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on 1point3acres Toolkit, and thousands of servers like it.
Across the catalogue