claim_next_agent_run

What claim_next_agent_run does on Todos

AI agents invoke claim_next_agent_run to trigger actions in Todos. 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 claim_next_agent_run is rated High

This tool initiates/triggers execution of an agent run—an operation whose effects depend on what the queued run contains. It is not merely reading (no data retrieval stated), not creating benign data reversibly (it claims exclusive execution control), and not destroying data. It is Execute-category because it transitions a task from queued to running state and hands control to an external agent.

From the tool's definition Tool claims (acquires/initiates) the next queued agent run. 'Claim' indicates state transition and operational control. Description uses 'atomically claim' suggesting transactional acquisition of execution rights.

The rule that runs claim_next_agent_run safely

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

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

Questions about claim_next_agent_run