finish_task_run · Todos MCP: Risk & Policy

WHAT IT DOES

What finish_task_run does on Todos

AI agents use finish_task_run to create or update resources in Todos — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Todos environment.

WHY IT NEEDS A POLICY

Why finish_task_run needs a policy

This tool updates/modifies the state of an existing task run record (marking it completed, failed, or cancelled). It is a state-change write operation on a ledger entry. It is reversible in principle (state could be changed again) and does not delete data, execute code, or involve finances. The idempotent lookup by key further confirms it is a controlled write/update operation.

From the tool's definition Finish a local run ledger entry as completed, failed, or cancelled

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

finish_task_run Rate-limited

finish_task_run stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "finish_task_run": {
      "limits": [
        {
          "counter": "finish_task_run_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

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 finish_task_run

What does the finish_task_run tool do? +

Finish a local run ledger entry as completed, failed, or cancelled. Supports idempotent lookup by key. It is categorised as a Write tool in the Todos MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on finish_task_run? +

Register the Todos MCP server in PolicyLayer and add a rule for finish_task_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 finish_task_run? +

finish_task_run is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit finish_task_run? +

Yes. Add a rate_limit block to the finish_task_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 finish_task_run completely? +

Set action: deny in the PolicyLayer policy for finish_task_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 finish_task_run? +

finish_task_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.