delete_entity_edge
AI agents call delete_entity_edge to permanently remove resources in KnowledgeSmith MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool deletes graph edges (relationships between entities), which is an irreversible operation. Combined with the sibling tool 'clear_graph' and the context of graph-based knowledge management, this removes data relationships that cannot be undone. Although the description is empty, the name and server context strongly indicate a destructive action.
From the tool's definition Tool name is 'delete_entity_edge' with 'delete' prefix, and the server description confirms 'complete CRUD functionality' including delete operations on structured document blocks and graph elements.
Attacks that exploit this kind of access
delete_entity_edge. It is categorised as a Destructive tool in the KnowledgeSmith MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the KnowledgeSmith MCP server in PolicyLayer and add a rule for delete_entity_edge: 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 KnowledgeSmith MCP. Nothing to install.
delete_entity_edge 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_entity_edge 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_entity_edge. 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_entity_edge is provided by the KnowledgeSmith MCP server (leo7nel23/knowledgesmith-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 →