Delete documents by ID or external ID
AI agents call delete_documents to permanently remove resources in PocketMCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes documents from the vector store and cannot be undone. Although the blast radius is somewhat limited to the local document collection rather than critical infrastructure, deletion of embedded documents in a development/IDE environment is irreversible and could cause loss of indexed knowledge.
From the tool's definition Tool name is 'delete_documents' and description states 'Delete documents by ID or external ID' — uses the verb 'delete' which indicates irreversible removal of data.
Attacks that exploit this kind of access
Delete documents by ID or external ID. It is categorised as a Destructive tool in the PocketMCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Pocket MCP server in PolicyLayer and add a rule for delete_documents: 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 PocketMCP. Nothing to install.
delete_documents 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_documents 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_documents. 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_documents is provided by the Pocket MCP server (kailash-sankar/pocketmcp). 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 →