nightly_run

Server Cockpit michielinksee/kansei-link-cockpit

Category Execute

Risk class High

Parameters 00 required

WHAT IT DOES

What nightly_run does on Cockpit

AI agents invoke nightly_run to trigger actions in Cockpit. 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 nightly_run needs a policy

This tool executes a complex, multi-company batch pipeline that automatically routes transactions through confidence-based decision logic and triggers downstream workflows (auto-approval, logging, human escalation).

From the tool's definition Processes ALL companies accessible by the token in batch mode; performs multi-stage classification pipeline with confidence routing; triggers automatic decision workflows (auto-approve for high confidence, auto-approve+log for medium, human routing for low);…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

nightly_run Rate-limited

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

FAQ

Questions about nightly_run

What does the nightly_run tool do? +

Nightly batch pipeline. Processes ALL companies accessible by the token (= multi-company batch). Pipeline per company: fetch unprocessed (status=unsettled) → Stage 0 exclusion → Stage 1+2 classify → confidence routing (high=auto, medium=auto+log, low=human_review) → aggregate summary. Currently dry-run only (write-back pending Phase 1.B). It is categorised as a Execute tool in the Cockpit MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on nightly_run? +

Register the Cockpit MCP server in PolicyLayer and add a rule for nightly_run: 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 nightly_run? +

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

Can I rate-limit nightly_run? +

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

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

nightly_run 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.