generate_issue_plan · CodeAudit MCP: Risk & Policy

WHAT IT DOES

What generate_issue_plan does on CodeAudit MCP

AI agents use generate_issue_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_issue_plan needs a policy

Although described as part of a 'read-only' server and the tool itself does not execute GitHub API calls to create actual issues, it produces structured output (issue candidates, labels, branch names) that represents authored content ready for write operations. This crosses from pure analysis (Read) into content generation (Write).

From the tool's definition Tool generates and groups findings into 'GitHub issue candidates' with structured metadata (labels, branch names), which constitutes creating or proposing new data structures that would typically be written to a tracking system or output format.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

generate_issue_plan Rate-limited

generate_issue_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_issue_plan": {
      "limits": [
        {
          "counter": "generate_issue_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_issue_plan

What does the generate_issue_plan tool do? +

Group findings into prioritized GitHub issue candidates with labels and branch names. 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_issue_plan? +

Register the CodeAudit MCP server in PolicyLayer and add a rule for generate_issue_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_issue_plan? +

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

Can I rate-limit generate_issue_plan? +

Yes. Add a rate_limit block to the generate_issue_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_issue_plan completely? +

Set action: deny in the PolicyLayer policy for generate_issue_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_issue_plan? +

generate_issue_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.