task_complete · AgentOS MCP: Risk & Policy

WHAT IT DOES

What task_complete does on AgentOS

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

WHY IT NEEDS A POLICY

Why task_complete needs a policy

This tool modifies task state reversibly—the task can be reopened or the state changed again. It does not delete data (not Destructive), execute arbitrary code (not Execute), involve financial operations (not Financial), or merely read data (not Read).

From the tool's definition Tool name 'task_complete' and description 'Mark a task as completed with final state' indicate a state modification operation. This creates or updates a task record's state field to 'completed'.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

task_complete Rate-limited

task_complete 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": {
    "task_complete": {
      "limits": [
        {
          "counter": "task_complete_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 AgentOS, so you can run agents against it safely.

FAQ

Questions about task_complete

What does the task_complete tool do? +

Mark a task as completed with final state. It is categorised as a Write tool in the AgentOS MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on task_complete? +

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

What risk level is task_complete? +

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

Can I rate-limit task_complete? +

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

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

task_complete is provided by the AgentOS MCP server (netflypsb/agentos). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.