cairntir_audit · Cairntir MCP: Risk & Policy

WHAT IT DOES

What cairntir_audit does on Cairntir

AI agents invoke cairntir_audit to trigger actions in Cairntir. 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 cairntir_audit needs a policy

This tool triggers execution of a Quality skill against a wing (likely a data partition in the SQLite memory system). While it doesn't delete data (not Destructive) or modify it directly (not purely Write), it executes an operation whose effects depend on arguments. The local-first nature and context of a memory system suggest this performs auditing/validation logic.

From the tool's definition 'Run the Quality skill over a wing' indicates execution of a skill/operation with effects dependent on which wing (data subset) is targeted. The verb 'run' and mention of a 'skill' suggest code or process execution.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

cairntir_audit Rate-limited

cairntir_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": {
    "cairntir_audit": {
      "limits": [
        {
          "counter": "cairntir_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 Cairntir, so you can run agents against it safely.

FAQ

Questions about cairntir_audit

What does the cairntir_audit tool do? +

Run the Quality skill over a wing. It is categorised as a Execute tool in the Cairntir MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on cairntir_audit? +

Register the Cairntir MCP server in PolicyLayer and add a rule for cairntir_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 Cairntir. Nothing to install.

What risk level is cairntir_audit? +

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

Can I rate-limit cairntir_audit? +

Yes. Add a rate_limit block to the cairntir_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 cairntir_audit completely? +

Set action: deny in the PolicyLayer policy for cairntir_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 cairntir_audit? +

cairntir_audit is provided by the Cairntir MCP server (pnmcguire480/cairntir). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.