planning_init · Codecks MCP: Risk & Policy

WHAT IT DOES

What planning_init does on Codecks

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

WHY IT NEEDS A POLICY

Why planning_init needs a policy

This tool creates new files in the project root directory. File creation is a Write operation—it modifies the filesystem by adding new resources, and these changes are reversible (files can be deleted or overwritten).

From the tool's definition Tool description states it 'Create[s]' files (task_plan.md, findings.md, progress.md) in project root. File creation is a reversible data modification action.

Risk signalsAdmin/system-level operation

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

planning_init Rate-limited

planning_init 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": {
    "planning_init": {
      "limits": [
        {
          "counter": "planning_init_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 Codecks, so you can run agents against it safely.

FAQ

Questions about planning_init

What does the planning_init tool do? +

Create lean planning files (task_plan.md, findings.md, progress.md) in project root. No auth needed. It is categorised as a Write tool in the Codecks MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on planning_init? +

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

What risk level is planning_init? +

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

Can I rate-limit planning_init? +

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

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

planning_init is provided by the Codecks MCP server (rangogamedev/codecks-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.