Delete an entity from the knowledge graph
AI agents call knowledge_delete_entity to permanently remove resources in Musubix — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deletion of knowledge graph entities cannot be undone and permanently removes data. This matches the Destructive category definition of irreversibly deleting or overwriting data. High severity because loss of knowledge graph data could have cascading impacts depending on the entity's role in downstream systems and processes. The action is unambiguous and the confidence is high.
From the tool's definition Tool name contains 'delete' and description states 'Delete an entity from the knowledge graph' — this is an irreversible removal operation.
Attacks that exploit this kind of access
Delete an entity from the knowledge graph. It is categorised as a Destructive tool in the Musubix MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Musubix MCP server in PolicyLayer and add a rule for knowledge_delete_entity: 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 Musubix. Nothing to install.
knowledge_delete_entity 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 knowledge_delete_entity 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 knowledge_delete_entity. 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.
knowledge_delete_entity is provided by the Musubix MCP server (@nahisaho/musubix-mcp-server). 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 →