Critical Risk →

delete_entities

Delete multiple entities and their associated relations from the knowledge graph

How to control delete_entities ↓

What delete_entities does on MCP Neo4j Knowledge Graph Memory Server

AI agents call delete_entities to permanently remove resources in MCP Neo4j Knowledge Graph Memory Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.

Critical Risk

Why delete_entities needs a policy

Deletion of entities from a persistent knowledge graph store is an irreversible destructive action. Unlike write operations that can be modified or undone, this operation permanently removes data and cascades to delete associated relations. The tool's capability to delete multiple entities in a single operation amplifies the blast radius if invoked incorrectly by an AI agent, making it high severity.

From the tool's definition Tool name is 'delete_entities' and description explicitly states it 'Delete multiple entities and their associated relations from the knowledge graph' — this irreversibly removes data and cannot be undone.

Documented attack patterns abuse exactly the kind of access delete_entities gives an agent:

How to control delete_entities

PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Neo4j Knowledge Graph Memory Server, and nothing reaches the server without passing your rules. This is the rule we recommend for delete_entities:

policy.json
{
  "version": "1",
  "default": "deny",
  "hide": [
    "delete_entities"
  ]
}

delete_entities disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.

  1. Create a free account and register MCP Neo4j Knowledge Graph Memory Server — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
RESTRICT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about delete_entities

What does the delete_entities tool do? +

Delete multiple entities and their associated relations from the knowledge graph. It is categorised as a Destructive tool in the MCP Neo4j Knowledge Graph Memory Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on delete_entities? +

Register the MCP Neo4j Knowledge Graph Memory Server MCP server in PolicyLayer and add a rule for delete_entities: 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 MCP Neo4j Knowledge Graph Memory Server. Nothing to install.

What risk level is delete_entities? +

delete_entities is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit delete_entities? +

Yes. Add a rate_limit block to the delete_entities 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.

How do I block delete_entities completely? +

Set action: deny in the PolicyLayer policy for delete_entities. 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.

What MCP server provides delete_entities? +

delete_entities is provided by the MCP Neo4j Knowledge Graph Memory Server MCP server (jovanhsu/mcp-neo4j-memory-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every MCP Neo4j Knowledge Graph Memory Server tool call.

Start from MCP Neo4j Knowledge Graph Memory 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.

8 MCP Neo4j Knowledge Graph Memory Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.