Destroy a document by ID and all of its associated chunks.
AI agents call destroy_document 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 performs an irreversible deletion operation that removes both a document record and all related data chunks from the knowledge base. The blast radius is high because an agent error could permanently lose significant amounts of indexed or stored information.
From the tool's definition The tool name 'destroy_document' combined with the description 'Destroy a document by ID and all of its associated chunks' indicates irreversible deletion.
Attacks that exploit this kind of access
Destroy a document by ID and all of its associated 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_document: 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_document 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_document 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_document. 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_document 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 →