Delete a memory from the knowledge base.
AI agents call kb_delete to permanently remove resources in Knowledge Base MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes data from persistent storage (ChromaDB-backed knowledge base). Deletion is not reversible. Although the blast radius is somewhat limited to a single memory item rather than the entire system, the irreversible nature and potential loss of important context or knowledge makes this a Destructive category tool.
From the tool's definition Tool name 'kb_delete' and description 'Delete a memory from the knowledge base' indicate irreversible removal of stored data.
Attacks that exploit this kind of access
Delete a memory from the knowledge base. It is categorised as a Destructive tool in the Knowledge Base MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Knowledge Base MCP Server MCP server in PolicyLayer and add a rule for kb_delete: 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 Knowledge Base MCP Server. Nothing to install.
kb_delete 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 kb_delete 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 kb_delete. 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.
kb_delete is provided by the Knowledge Base MCP Server MCP server (leon4s4/knowledge-base-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 →