delete_portfolio
AI agents call delete_portfolio to permanently remove resources in Portfolio — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deletion of portfolio records is irreversible and cannot be undone. Given the context of a portfolio management system, this tool would permanently remove investment portfolio data, representing a high blast radius if invoked by an AI agent on the wrong portfolio or without authorization. Even with an empty description, the verb 'delete' clearly maps to the Destructive category per classification rules.
From the tool's definition Tool name is 'delete_portfolio' which explicitly indicates deletion of portfolio data. Description is empty, but the naming convention is unambiguous—'delete' is a destructive operation.
Attacks that exploit this kind of access
delete_portfolio. It is categorised as a Destructive tool in the Portfolio MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Portfolio MCP server in PolicyLayer and add a rule for delete_portfolio: 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 Portfolio. Nothing to install.
delete_portfolio 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 delete_portfolio 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 delete_portfolio. 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.
delete_portfolio is provided by the Portfolio MCP server (l4b4r4b4b4/portfolio-mcp). 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 →