Delete a project by title
AI agents call delete_project 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.
This tool permanently removes project data from the portfolio. Destructive operations rank higher than Write or Execute in severity hierarchy. The blast radius is high: an AI agent with incorrect title matching or malicious intent could remove important portfolio projects. This warrants high severity despite the straightforward nature of the operation.
From the tool's definition Tool name is 'delete_project' with description 'Delete a project by title'. The verb 'delete' and the action of removing a project irreversibly constitute a destructive operation that cannot be undone without external recovery means.
Attacks that exploit this kind of access
Delete a project by title. 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_project: 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_project 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_project 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_project. 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_project is provided by the Portfolio MCP server (sohumsuthar/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 →