run_audit · Plurity MCP: Risk & Policy

WHAT IT DOES

What run_audit does on Plurity

AI agents invoke run_audit to trigger actions in Plurity. 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 run_audit needs a policy

The 'run' verb indicates active execution rather than passive read. While 'audit' itself is not inherently destructive (audit operations typically scan without modifying), executing an audit scan is an Execute-category action—it triggers external operations and side effects (scan resources, generate reports, potentially trigger downstream processes).

From the tool's definition Tool name 'run_audit' with 'run' prefix indicates execution of an audit operation. Server context shows this is part of Plurity's Audit service for 'GEO readiness' scanning.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_audit Rate-limited

run_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": {
    "run_audit": {
      "limits": [
        {
          "counter": "run_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 Plurity, so you can run agents against it safely.

FAQ

Questions about run_audit

What does the run_audit tool do? +

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

How do I enforce a policy on run_audit? +

Register the Plurity MCP server in PolicyLayer and add a rule for run_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 Plurity. Nothing to install.

What risk level is run_audit? +

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

Can I rate-limit run_audit? +

Yes. Add a rate_limit block to the run_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 run_audit completely? +

Set action: deny in the PolicyLayer policy for run_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 run_audit? +

run_audit is provided by the Plurity MCP server (plurity-ai/plurity-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.