codegen_clean · Pen MCP: Risk & Policy

WHAT IT DOES

What codegen_clean does on Pen

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

WHY IT NEEDS A POLICY

Why codegen_clean needs a policy

This tool modifies state (cleaning up/removing a codegen plan) but does not irreversibly delete it—'clean up' suggests organized removal or reset of an abandoned plan. The idempotent nature and context within a document/code generation manager (OpenPencil) suggests data reorganization rather than destruction.

From the tool's definition Tool name 'codegen_clean' and description 'Manually clean up an abandoned codegen plan' indicates modification/cleanup of existing data structures.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

codegen_clean Rate-limited

codegen_clean 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": {
    "codegen_clean": {
      "limits": [
        {
          "counter": "codegen_clean_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 Pen, so you can run agents against it safely.

FAQ

Questions about codegen_clean

What does the codegen_clean tool do? +

Manually clean up an abandoned codegen plan. Idempotent. It is categorised as a Write tool in the Pen MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on codegen_clean? +

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

What risk level is codegen_clean? +

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

Can I rate-limit codegen_clean? +

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

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

codegen_clean is provided by the Pen MCP server (@zseven-w/pen-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.