retry_agent_run_dispatch · Todos MCP: Risk & Policy

WHAT IT DOES

What retry_agent_run_dispatch does on Todos

AI agents invoke retry_agent_run_dispatch 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_dispatch needs a policy

This tool queues/schedules the re-execution of a previous agent dispatch—a computational operation whose side effects depend on what the original dispatch did. It is Execute rather than Write because it triggers external agent operations (not merely data creation) and rather than Read because it initiates a process with potential side effects.

From the tool's definition Tool name contains 'retry' and 'dispatch'; description states it 'Queue[s] a retry for a previous local agent dispatch.' This triggers re-execution of a prior agent operation.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

retry_agent_run_dispatch Rate-limited

retry_agent_run_dispatch 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_dispatch": {
      "limits": [
        {
          "counter": "retry_agent_run_dispatch_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_dispatch

What does the retry_agent_run_dispatch tool do? +

Queue a retry for a previous local agent dispatch. 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_dispatch? +

Register the Todos MCP server in PolicyLayer and add a rule for retry_agent_run_dispatch: 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_dispatch? +

retry_agent_run_dispatch 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_dispatch? +

Yes. Add a rate_limit block to the retry_agent_run_dispatch 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_dispatch completely? +

Set action: deny in the PolicyLayer policy for retry_agent_run_dispatch. 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_dispatch? +

retry_agent_run_dispatch 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.