Delete session directories that have been cancelled or completed.
AI agents call finslipa_clean to permanently remove resources in Finsliparn — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deletion of session directories is irreversible and cannot be undone. Although the scope appears limited to completed or cancelled sessions rather than live data, the operation destroys persistent state and artifacts. This qualifies as Destructive rather than Write.
From the tool's definition Tool name contains 'clean' and description explicitly states 'Delete session directories'—direct use of delete verb applied to data/artifacts.
Attacks that exploit this kind of access
Delete session directories that have been cancelled or completed. It is categorised as a Destructive tool in the Finsliparn MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Finsliparn MCP server in PolicyLayer and add a rule for finslipa_clean: 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 Finsliparn. Nothing to install.
finslipa_clean 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 finslipa_clean 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 finslipa_clean. 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.
finslipa_clean is provided by the Finsliparn MCP server (jgabor/finsliparn). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →