transkribus_job_restart_all_by_user

What transkribus_job_restart_all_by_user does on Transkribus

AI agents invoke transkribus_job_restart_all_by_user to trigger actions in Transkribus. 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 transkribus_job_restart_all_by_user is rated High

This tool executes an action (restart) on multiple jobs owned by a user, which is an external operation with real consequences for system state and running processes. It does not retrieve data (Read), modify data reversibly in a user-controllable way (Write), or destroy data (Destructive). However, it does trigger a bulk action whose outcome depends on the argument (user identifier), matching the Execute category.

From the tool's definition Tool name includes 'restart' and description states 'Restart all jobs for a specific user' — this triggers external operations (job restart) whose effects depend on which user is targeted.

The rule that runs transkribus_job_restart_all_by_user safely

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

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

Questions about transkribus_job_restart_all_by_user