schedule_task · Things Cloud MCP: Risk & Policy

WHAT IT DOES

What schedule_task does on Things Cloud MCP

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

WHY IT NEEDS A POLICY

Why schedule_task needs a policy

Scheduling a task modifies task state (adds/changes a date/time property) reversibly. This is a write operation, not destructive (can be unscheduled), not execute (doesn't run code), and not financial. Severity is medium because misuse could create unwanted task clutter or scheduling chaos, but the blast radius is limited to the user's task list.

From the tool's definition Tool name 'schedule_task' on a Things Cloud MCP server that provides 'read/write access to your Things3 tasks'. Sibling tools include create_task, complete_task, assign_tags, and other task modifications, establishing the server's write-capable purpose.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

schedule_task Rate-limited

schedule_task 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": {
    "schedule_task": {
      "limits": [
        {
          "counter": "schedule_task_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 Things Cloud MCP, so you can run agents against it safely.

FAQ

Questions about schedule_task

What does the schedule_task tool do? +

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

How do I enforce a policy on schedule_task? +

Register the Things Cloud MCP server in PolicyLayer and add a rule for schedule_task: 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 Things Cloud MCP. Nothing to install.

What risk level is schedule_task? +

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

Can I rate-limit schedule_task? +

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

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

schedule_task is provided by the Things Cloud MCP server (nkootstra/things). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.