claim_next_agent_run · Todos MCP: Risk & Policy

WHAT IT DOES

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 IT NEEDS A POLICY

Why claim_next_agent_run needs a policy

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.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

claim_next_agent_run Rate-limited

claim_next_agent_run 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.

View as policy code

policy.json

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

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Todos, so you can run agents against it safely.

FAQ

Questions about claim_next_agent_run

What does the claim_next_agent_run tool do? +

Atomically claim the next queued local agent run. It is categorised as a Execute tool in the Todos MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on claim_next_agent_run? +

Register the Todos MCP server in PolicyLayer and add a rule for claim_next_agent_run: 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 Todos. Nothing to install.

What risk level is claim_next_agent_run? +

claim_next_agent_run is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit claim_next_agent_run? +

Yes. Add a rate_limit block to the claim_next_agent_run 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.

How do I block claim_next_agent_run completely? +

Set action: deny in the PolicyLayer policy for claim_next_agent_run. 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.

What MCP server provides claim_next_agent_run? +

claim_next_agent_run is provided by the Todos MCP server (@hasna/todos). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.