Critical Risk →

cleanup

Run memory decay and eviction. Expires facts past their TTL and evicts low-salience facts when memory exceeds capacity. Call periodically in long-running agent sessions to prevent unbounded growth. Side effects: DESTRUCTIVE — permanently removes evicted and expired facts (irreversible). Auth: req...

Part of the Nocturnusai server.

cleanup can permanently delete data in Nocturnusai, with no limits today. PolicyLayer puts allow, deny, and rate-limit rules on every call. Live in minutes.

SECURE NOCTURNUSAI →

Free to start. No card required.

AI agents may call cleanup to permanently remove or destroy resources in Nocturnusai. Without a policy, an autonomous agent could delete critical data in a loop with no way to undo the damage. PolicyLayer blocks destructive tools by default and requires explicit human approval before enabling them.

Without a policy, an AI agent could call cleanup in a loop, permanently destroying resources in Nocturnusai. There is no undo for destructive operations. PolicyLayer blocks this tool by default and only allows it when a human explicitly approves the action.

Destructive tools permanently remove data. Block by default. Only enable with explicit approval workflows.

policy.json
{
  "version": "1",
  "default": "deny",
  "hide": [
    "cleanup"
  ]
}

See the full Nocturnusai policy for all 16 tools.

Get this rule live on your own Nocturnusai server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY NOCTURNUSAI →

View all 16 tools →

These attack patterns abuse exactly the kind of access cleanup gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so cleanup only ever does what you allow.

SECURE NOCTURNUSAI →

Other destructive tools across the catalogue. The same approach applies to each: deny by default, or require human approval.

What does the cleanup tool do? +

Run memory decay and eviction. Expires facts past their TTL and evicts low-salience facts when memory exceeds capacity. Call periodically in long-running agent sessions to prevent unbounded growth. Side effects: DESTRUCTIVE — permanently removes evicted and expired facts (irreversible). Auth: requires X-Tenant-ID header; FACT_WRITE permission when auth is enabled. Rate-limited per principal. Errors: VALIDATION_ERROR on bad threshold.. It is categorised as a Destructive tool in the Nocturnusai MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on cleanup? +

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

What risk level is cleanup? +

cleanup is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit cleanup? +

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

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

cleanup is provided by the Nocturnusai MCP server (nocturnusai-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Nocturnusai tool call.

Deterministic rules across all 16 Nocturnusai tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.