dispatch_tasks · Todos MCP: Risk & Policy

WHAT IT DOES

What dispatch_tasks does on Todos

AI agents invoke dispatch_tasks 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_tasks needs a policy

This tool triggers execution of external operations (task dispatch to tmux) whose concrete side effects are data-dependent and cannot be predicted without knowing task payloads. While it requires explicit human choice as a safeguard, an AI agent with access could dispatch arbitrary tasks to terminal sessions, executing shell commands or workflows with uncontrolled blast radius.

From the tool's definition Tool sends tasks to a tmux window (a terminal multiplexer), triggering external command execution. The description explicitly states 'send specific tasks to a tmux window' and references 'scheduled sending', indicating the tool executes operations whose…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

dispatch_tasks Rate-limited

dispatch_tasks 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_tasks": {
      "limits": [
        {
          "counter": "dispatch_tasks_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_tasks

What does the dispatch_tasks tool do? +

Legacy/emergency only: send specific tasks to a tmux window after a human explicitly chooses tmux delivery. Normal pending-task routing should use task-created headless workflows. Supports dry-run preview 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_tasks? +

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

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

Can I rate-limit dispatch_tasks? +

Yes. Add a rate_limit block to the dispatch_tasks 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_tasks completely? +

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

dispatch_tasks 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.