dispatch_task_list · Todos MCP: Risk & Policy

WHAT IT DOES

What dispatch_task_list does on Todos

AI agents invoke dispatch_task_list 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 dispatch_task_list needs a policy

This tool dispatches tasks to a tmux window, triggering external execution of commands/workflows. Sending tasks to tmux implies executing shell-level operations in a terminal session. The 'send all tasks' scope combined with tmux execution makes misuse high-severity, as an AI agent could trigger broad unintended command execution. Dry-run support confirms real execution is the primary mode.

From the tool's definition "send all tasks from a task list to a tmux window" and "Supports filtering, dry-run, and scheduled sending"

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

dispatch_task_list Rate-limited

dispatch_task_list 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": {
    "dispatch_task_list": {
      "limits": [
        {
          "counter": "dispatch_task_list_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 dispatch_task_list

What does the dispatch_task_list tool do? +

Legacy/emergency only: send all tasks from a task list to a tmux window after a human explicitly chooses tmux delivery. Normal pending-task routing should use task-created headless workflows. Supports filtering, dry-run, and scheduled sending. 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 dispatch_task_list? +

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

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

Can I rate-limit dispatch_task_list? +

Yes. Add a rate_limit block to the dispatch_task_list 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 dispatch_task_list completely? +

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

dispatch_task_list 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.