Destroy a corpus and all its associated documents and chunks.
AI agents call destroy_corpus to permanently remove resources in Pgmcp — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently deletes a corpus along with all dependent documents and chunks. This is irreversible data loss with potentially broad scope. It does not move money (ruling out Financial), does not execute arbitrary code (Execute), and is more severe than Write since it cannot be reversed.
From the tool's definition Tool name 'destroy_corpus' combined with description 'Destroy a corpus and all its associated documents and chunks' explicitly indicates irreversible deletion of data.
Attacks that exploit this kind of access
Destroy a corpus and all its associated documents and chunks. It is categorised as a Destructive tool in the Pgmcp MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Pg MCP server in PolicyLayer and add a rule for destroy_corpus: 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 Pgmcp. Nothing to install.
destroy_corpus 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 destroy_corpus 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 destroy_corpus. 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.
destroy_corpus is provided by the Pg MCP server (veloper/pgmcp). 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 →