Permanently delete a project
AI agents call memvid_delete_project to permanently remove resources in Memvid — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool performs permanent deletion, which cannot be undone. This is a destructive operation that removes project data entirely. While the blast radius is limited to a single project context (not critical), the irreversible nature of deletion and potential loss of important work justifies 'high' severity in the Destructive category.
From the tool's definition Tool name 'memvid_delete_project' combined with description 'Permanently delete a project' explicitly indicates irreversible deletion of data.
Attacks that exploit this kind of access
Permanently delete a project. It is categorised as a Destructive tool in the Memvid MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Memvid MCP server in PolicyLayer and add a rule for memvid_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 Memvid. Nothing to install.
memvid_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 memvid_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 memvid_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.
memvid_delete_project is provided by the Memvid MCP server (memvid-mcp-server). 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 →