Remove a document from the knowledge base.
AI agents call remove_document to permanently remove resources in TDZ C64 Knowledge — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly deletes documents from the knowledge base. Once removed, the document's indexed content and associated metadata are lost and cannot be recovered through the tool itself. This is a destructive operation with no undo mechanism described.
From the tool's definition Tool name is 'remove_document' with description 'Remove a document from the knowledge base.' The verb 'remove' in the context of a knowledge base indicates deletion or permanent removal of indexed content.
Attacks that exploit this kind of access
Remove a document from the knowledge base. It is categorised as a Destructive tool in the TDZ C64 Knowledge MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the TDZ C64 Knowledge MCP server in PolicyLayer and add a rule for remove_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 TDZ C64 Knowledge. Nothing to install.
remove_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 remove_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 remove_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.
remove_document is provided by the TDZ C64 Knowledge MCP server (michaeltroelsen/tdz-c64-knowledge). 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 →