generate_pr_plan · CodeAudit MCP: Risk & Policy

WHAT IT DOES

What generate_pr_plan does on CodeAudit MCP

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

WHY IT NEEDS A POLICY

Why generate_pr_plan needs a policy

This tool creates (writes) PR workflow plans as data artifacts, but within a read-only auditing context. It does not execute code, delete data, or trigger actual repository changes—it only generates planning documents. The 'low' severity reflects that the worst-case misuse would be creating misleading or duplicative workflow plans, which are reversible and non-destructive.

From the tool's definition Tool description states 'Create a scoped PR workflow' which indicates it generates or creates plan artifacts. The server is explicitly 'read-only' for inspection and planning purposes, with no capability to actually push code or modify repositories.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

generate_pr_plan Rate-limited

generate_pr_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": {
    "generate_pr_plan": {
      "limits": [
        {
          "counter": "generate_pr_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 CodeAudit MCP, so you can run agents against it safely.

FAQ

Questions about generate_pr_plan

What does the generate_pr_plan tool do? +

Create a scoped PR workflow from selected findings or an issue candidate. It is categorised as a Write tool in the CodeAudit MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on generate_pr_plan? +

Register the CodeAudit MCP server in PolicyLayer and add a rule for generate_pr_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 CodeAudit MCP. Nothing to install.

What risk level is generate_pr_plan? +

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

Can I rate-limit generate_pr_plan? +

Yes. Add a rate_limit block to the generate_pr_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 generate_pr_plan completely? +

Set action: deny in the PolicyLayer policy for generate_pr_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 generate_pr_plan? +

generate_pr_plan is provided by the CodeAudit MCP server (priyanshuchawda/codeaudit). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.