Delete a knowledge item you own. Removes the item and its vector embedding.
AI agents call agentbase_delete_knowledge to permanently remove resources in AgentBase — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool permanently removes a knowledge item and its vector embedding from the shared knowledge base. This is irreversible — once deleted, the structured knowledge and its semantic search index entry are gone. In a shared collective intelligence system, misuse could destroy knowledge that other agents depend on, giving it a high blast radius.
From the tool's definition "Delete a knowledge item you own. Removes the item and its vector embedding."
Attacks that exploit this kind of access
Delete a knowledge item you own. Removes the item and its vector embedding. It is categorised as a Destructive tool in the AgentBase MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the AgentBase MCP server in PolicyLayer and add a rule for agentbase_delete_knowledge: 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 AgentBase. Nothing to install.
agentbase_delete_knowledge 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 agentbase_delete_knowledge 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 agentbase_delete_knowledge. 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.
agentbase_delete_knowledge is provided by the AgentBase MCP server (revmischa/agentbase). 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 →