taskComplete · Routine MCP: Risk & Policy

WHAT IT DOES

What taskComplete does on Routine

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

WHY IT NEEDS A POLICY

Why taskComplete needs a policy

Completing a task modifies task status/state data but does not delete or destroy the task, nor does it execute arbitrary code or move money. It is reversible (a task can be reopened). This is a straightforward Write operation with low severity since the blast radius of accidental completion is limited—tasks can be uncompleted or reviewed.

From the tool's definition Tool name 'taskComplete' and description 'Complete a task' indicates marking an existing task as done, which is a reversible state change to task metadata.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

taskComplete Rate-limited

taskComplete 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": {
    "taskComplete": {
      "limits": [
        {
          "counter": "taskcomplete_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 Routine, so you can run agents against it safely.

FAQ

Questions about taskComplete

What does the taskComplete tool do? +

Complete a task. It is categorised as a Write tool in the Routine MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on taskComplete? +

Register the Routine MCP server in PolicyLayer and add a rule for taskComplete: 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 Routine. Nothing to install.

What risk level is taskComplete? +

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

Can I rate-limit taskComplete? +

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

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

taskComplete is provided by the Routine MCP server (routineco/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.