Delete an alert
AI agents call delete_alert to permanently remove resources in My Portfolio MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes alert records from the portfolio management system. While alerts themselves are typically metadata rather than core financial holdings, their deletion is irreversible and could impact risk monitoring and compliance. An AI agent misusing this could remove important price alerts, compliance notifications, or audit records.
From the tool's definition Tool name is 'delete_alert' with description 'Delete an alert'. The verb 'delete' indicates irreversible removal of data.
Attacks that exploit this kind of access
Delete an alert. It is categorised as a Destructive tool in the My Portfolio MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the My Portfolio MCP Server MCP server in PolicyLayer and add a rule for delete_alert: 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 My Portfolio MCP Server. Nothing to install.
delete_alert 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_alert 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_alert. 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_alert is provided by the My Portfolio MCP Server MCP server (udaybhasker-ub/my-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 →