Memory maintenance: decay (exponential, halflife=30d), prune (remove low-importance), merge (deduplicate), summarize (compress observations), pagerank (personalized importance), find_duplicates, export, stats.
Part of the Pypi:cuba Memorys server.
Free to start. No card required.
AI agents may call cuba_zafra to permanently remove or destroy resources in Pypi:cuba Memorys. 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 cuba_zafra in a loop, permanently destroying resources in Pypi:cuba Memorys. 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.
{
"version": "1",
"default": "deny",
"hide": [
"cuba_zafra"
]
}See the full Pypi:cuba Memorys policy for all 13 tools.
These attack patterns abuse exactly the kind of access cuba_zafra gives an agent. Each links to the full case and the policy that stops it:
Other destructive tools across the catalogue. The same approach applies to each: deny by default, or require human approval.
Memory maintenance: decay (exponential, halflife=30d), prune (remove low-importance), merge (deduplicate), summarize (compress observations), pagerank (personalized importance), find_duplicates, export, stats.. It is categorised as a Destructive tool in the Pypi:cuba Memorys MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Pypi:cuba Memorys MCP server in PolicyLayer and add a rule for cuba_zafra: 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 Pypi:cuba Memorys. Nothing to install.
cuba_zafra is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the cuba_zafra 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.
Set action: deny in the PolicyLayer policy for cuba_zafra. 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.
cuba_zafra is provided by the Pypi:cuba Memorys MCP server (LeandroPG19/cuba-memorys). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 13 Pypi:cuba Memorys 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.