retry_agent_run · Todos MCP: Risk & Policy

WHAT IT DOES

What retry_agent_run does on Todos

AI agents invoke retry_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 retry_agent_run needs a policy

This tool triggers the re-execution of an agent run, which constitutes executing code or commands whose effects depend on the agent's actions and arguments. While not immediately destructive, a retry can cause the agent to repeat potentially harmful operations (data writes, API calls, file modifications), making it Execute rather than Write.

From the tool's definition The tool 're-queues' a failed or cancelled agent run, triggering the re-execution of an autonomous agent's workflow.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

retry_agent_run Rate-limited

retry_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": {
    "retry_agent_run": {
      "limits": [
        {
          "counter": "retry_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 retry_agent_run

What does the retry_agent_run tool do? +

Manually re-queue a failed or cancelled 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 retry_agent_run? +

Register the Todos MCP server in PolicyLayer and add a rule for retry_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 retry_agent_run? +

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

Can I rate-limit retry_agent_run? +

Yes. Add a rate_limit block to the retry_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 retry_agent_run completely? +

Set action: deny in the PolicyLayer policy for retry_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 retry_agent_run? +

retry_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.