create_plan · Melo MCP: Risk & Policy

WHAT IT DOES

What create_plan does on Melo

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

WHY IT NEEDS A POLICY

Why create_plan needs a policy

This tool creates a new plan object with up to 20 steps, which is a reversible creation operation. It does not delete data (ruling out Destructive), does not execute arbitrary code (ruling out Execute), involves no financial transactions (ruling out Financial), and is more than a simple read operation. The ability to subsequently modify steps via update_plan_step suggests the plan is a modifiable data structure.

From the tool's definition Tool name 'create_plan' and description 'Create a Planning Mode plan' with mention of returning a planId for subsequent operations indicate creation of a new data structure/plan object.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

create_plan Rate-limited

create_plan 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": {
    "create_plan": {
      "limits": [
        {
          "counter": "create_plan_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 Melo, so you can run agents against it safely.

FAQ

Questions about create_plan

What does the create_plan tool do? +

Create a Planning Mode plan with up to 20 steps. Returns a planId you reference from update_plan_step and snapshot_checkpoint. Steps default to verifyWith=. It is categorised as a Write tool in the Melo MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on create_plan? +

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

What risk level is create_plan? +

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

Can I rate-limit create_plan? +

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

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

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