AI agents call delete_knowledge_base to permanently remove resources in WeKnora MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting a knowledge base is an irreversible operation that removes an entire collection of data. This cannot be undone and represents the most severe category of risk. The blast radius is significant—an AI agent instructed or tricked into deleting the wrong knowledge base could cause substantial data loss. While not financial, this is worse than Execute or Write operations.
From the tool's definition Tool name is 'delete_knowledge_base' and description states 'Delete a knowledge base'. The verb 'delete' combined with the scope of 'knowledge base' (a container that likely holds multiple knowledge items) indicates irreversible removal of data.
Documented attack patterns abuse exactly the kind of access delete_knowledge_base gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and WeKnora MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for delete_knowledge_base:
{
"version": "1",
"default": "deny",
"hide": [
"delete_knowledge_base"
]
}delete_knowledge_base disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Delete a knowledge base. It is categorised as a Destructive tool in the WeKnora MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the WeKnora MCP Server MCP server in PolicyLayer and add a rule for delete_knowledge_base: 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 WeKnora MCP Server. Nothing to install.
delete_knowledge_base 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_knowledge_base 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_knowledge_base. 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_knowledge_base is provided by the WeKnora MCP Server MCP server (nannaolympicbroadcast/weknoramcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from WeKnora MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
21 WeKnora MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.