stop_pipeline_job_run

What stop_pipeline_job_run does on Alibabacloud Devops

AI agents invoke stop_pipeline_job_run to trigger actions in Alibabacloud Devops. 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 stop_pipeline_job_run is rated High

This is Execute rather than Write because it doesn't create or modify data reversibly; it terminates an active operation. It's not Destructive because stopping a job doesn't irreversibly delete data or make un-undoable changes (the job can typically be restarted). The blast radius is high: an AI agent misconfiguring the job ID could halt critical CI/CD workflows, blocking deployments or builds.

From the tool's definition The tool 'stop_pipeline_job_run' performs an action that 'Stop/terminate a running pipeline job' — this directly triggers an external operation (terminating an active process) whose effects depend on which pipeline job is targeted.

The rule that runs stop_pipeline_job_run safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Alibabacloud Devops, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For stop_pipeline_job_run, this is the rule to start with:

{
  "version": "1",
  "default": "deny",
  "tools": {
    "stop_pipeline_job_run": {
      "limits": [
        {
          "counter": "stop_pipeline_job_run_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

Questions about stop_pipeline_job_run