correct_classification · Cockpit MCP: Risk & Policy

WHAT IT DOES

What correct_classification does on Cockpit

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

WHY IT NEEDS A POLICY

Why correct_classification needs a policy

This tool writes a persistent correction record that modifies future classification behavior globally or per-company. It creates/updates durable memory entries (equivalent to a persistent memory layer) that automatically reroute future transaction classifications.

From the tool's definition 誤分類を記録し、同パターンの取引が今後来たら修正後の勘定科目を自動適用。永続記憶、二度と同じ誤りをしない。修正は全社共通 or 特定会社のみに適用可能。

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

correct_classification Rate-limited

correct_classification 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": {
    "correct_classification": {
      "limits": [
        {
          "counter": "correct_classification_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 Cockpit, so you can run agents against it safely.

FAQ

Questions about correct_classification

What does the correct_classification tool do? +

税理士修正フィードバック。誤分類を記録し、同パターンの取引が今後来たら修正後の勘定科目を自動適用。Linksee Memory caveat layer と同等（= 永続記憶、二度と同じ誤りをしない）。修正は全社共通 or 特定会社のみに適用可能。. It is categorised as a Write tool in the Cockpit MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on correct_classification? +

Register the Cockpit MCP server in PolicyLayer and add a rule for correct_classification: 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 Cockpit. Nothing to install.

What risk level is correct_classification? +

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

Can I rate-limit correct_classification? +

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

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

correct_classification is provided by the Cockpit MCP server (michielinksee/kansei-link-cockpit). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.