complete_agent_run · Todos MCP: Risk & Policy

WHAT IT DOES

What complete_agent_run does on Todos

AI agents use complete_agent_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 complete_agent_run needs a policy

This tool modifies the state of an agent run (marking it as completed) but does not execute code, delete data, or move money. It is a write operation that changes metadata/status of a task run record. Severity is medium because incorrect completion status could mislead task tracking and coordination between agents, but the change is typically reversible (can be re-opened or corrected).

From the tool's definition Tool name 'complete_agent_run' and description 'Mark a running agent run as completed' indicates state modification of an existing agent run record.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

complete_agent_run Rate-limited

complete_agent_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": {
    "complete_agent_run": {
      "limits": [
        {
          "counter": "complete_agent_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 complete_agent_run

What does the complete_agent_run tool do? +

Mark a running agent run as completed with optional evidence. 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 complete_agent_run? +

Register the Todos MCP server in PolicyLayer and add a rule for complete_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 complete_agent_run? +

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

Can I rate-limit complete_agent_run? +

Yes. Add a rate_limit block to the complete_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 complete_agent_run completely? +

Set action: deny in the PolicyLayer policy for complete_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 complete_agent_run? +

complete_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.