plan_task · Mol MCP: Risk & Policy

WHAT IT DOES

What plan_task does on Molmcp

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

WHY IT NEEDS A POLICY

Why plan_task needs a policy

An AI agent can call plan_task faster than any human can review — one bad instruction and it creates or modifies resources in Molmcp by the hundred, each call as confident as the last.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

plan_task Rate-limited

plan_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": {
    "plan_task": {
      "limits": [
        {
          "counter": "plan_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 Molmcp, so you can run agents against it safely.

FAQ

Questions about plan_task

What does the plan_task tool do? +

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

How do I enforce a policy on plan_task? +

Register the Mol MCP server in PolicyLayer and add a rule for plan_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 Molmcp. Nothing to install.

What risk level is plan_task? +

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

Can I rate-limit plan_task? +

Yes. Add a rate_limit block to the plan_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 plan_task completely? +

Set action: deny in the PolicyLayer policy for plan_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 plan_task? +

plan_task is provided by the Mol MCP server (molcrafts/molmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.