code_for_plan · AI Pull Request Generator MCP: Risk & Policy

WHAT IT DOES

What code_for_plan does on AI Pull Request Generator

AI agents invoke code_for_plan to trigger actions in AI Pull Request Generator. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why code_for_plan needs a policy

Based on the server context, this tool likely generates and possibly executes or writes code as part of the automated PR workflow. The name suggests it produces code for a given plan, which would be at minimum a Write operation (generating code artifacts), potentially Execute if it runs or applies the code. Given sibling tools handle planning and PR creation separately, this tool most likely generates/writes code.

From the tool's definition Tool name 'code_for_plan' combined with server description: 'automates the process of planning tasks, generating code, and creating GitHub pull requests.' No explicit description provided for the tool itself.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

code_for_plan Rate-limited

code_for_plan stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "code_for_plan": {
      "limits": [
        {
          "counter": "code_for_plan_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches AI Pull Request Generator, so you can run agents against it safely.

FAQ

Questions about code_for_plan

What does the code_for_plan tool do? +

code_for_plan. It is categorised as a Execute tool in the AI Pull Request Generator MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on code_for_plan? +

Register the AI Pull Request Generator MCP server in PolicyLayer and add a rule for code_for_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 AI Pull Request Generator. Nothing to install.

What risk level is code_for_plan? +

code_for_plan is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit code_for_plan? +

Yes. Add a rate_limit block to the code_for_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 code_for_plan completely? +

Set action: deny in the PolicyLayer policy for code_for_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 code_for_plan? +

code_for_plan is provided by the AI Pull Request Generator MCP server (shougakusei/plan_pr_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.