Delete a concept from the knowledge base.
AI agents call delete_concept to permanently remove resources in Concept Tracker — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes concept records from a knowledge base, which cannot be easily undone. While not as critical as deleting code or financial data, deletion of organized knowledge structures represents a destructive action with potential loss of information architecture and references.
From the tool's definition Tool name is 'delete_concept' and description states 'Delete a concept from the knowledge base.' The verb 'delete' combined with removal from a knowledge base indicates irreversible data removal.
Attacks that exploit this kind of access
Delete a concept from the knowledge base. It is categorised as a Destructive tool in the Concept Tracker MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Concept Tracker MCP server in PolicyLayer and add a rule for delete_concept: 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 Concept Tracker. Nothing to install.
delete_concept 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_concept 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_concept. 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_concept is provided by the Concept Tracker MCP server (liwengggou/mcp). 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 →