codeguard_audit · Code Guard Ai MCP: Risk & Policy

WHAT IT DOES

What codeguard_audit does on Code Guard Ai

AI agents invoke codeguard_audit to trigger actions in Code Guard Ai. 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 codeguard_audit needs a policy

The tool actively runs an audit process across the repository, triggering external LLM calls (GPT-4o, Claude, DeepSeek) and scanning code. This goes beyond passive reading — it executes an analysis pipeline with external service calls.

From the tool's definition 'Runs deep compliance audit' on 'the current repository' — actively executes analysis across a codebase using multiple LLMs

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

codeguard_audit Rate-limited

codeguard_audit 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": {
    "codeguard_audit": {
      "limits": [
        {
          "counter": "codeguard_audit_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 Code Guard Ai, so you can run agents against it safely.

FAQ

Questions about codeguard_audit

What does the codeguard_audit tool do? +

Runs deep compliance audit (GDPR/LGPD/PCI) on the current repository. It is categorised as a Execute tool in the Code Guard Ai MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on codeguard_audit? +

Register the Code Guard Ai MCP server in PolicyLayer and add a rule for codeguard_audit: 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 Code Guard Ai. Nothing to install.

What risk level is codeguard_audit? +

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

Can I rate-limit codeguard_audit? +

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

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

codeguard_audit is provided by the Code Guard Ai MCP server (negraodenio/code-guard-ai). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.