Critical Risk →

delete_connection

Delete a specific connection between two memories

How to control delete_connection ↓

What delete_connection does on Neo4j Agent Memory MCP Server

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

Critical Risk

Why delete_connection needs a policy

This tool permanently removes semantic relationships (edges) between memory nodes. While not as severe as deleting entire memories, deletion of connections is irreversible and could break important contextual links that an AI agent relies on for reasoning and decision-making. An AI agent could maliciously or erroneously sever critical knowledge connections, degrading memory integrity.

From the tool's definition Tool name 'delete_connection' and description 'Delete a specific connection between two memories' explicitly perform irreversible deletion of graph relationships in the Neo4j memory store.

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

How to control delete_connection

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

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

delete_connection 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 Neo4j Agent Memory MCP 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_connection

What does the delete_connection tool do? +

Delete a specific connection between two memories. It is categorised as a Destructive tool in the Neo4j Agent Memory MCP 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_connection? +

Register the Neo4j Agent Memory MCP Server MCP server in PolicyLayer and add a rule for delete_connection: 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 Neo4j Agent Memory MCP Server. Nothing to install.

What risk level is delete_connection? +

delete_connection 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_connection? +

Yes. Add a rate_limit block to the delete_connection 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_connection completely? +

Set action: deny in the PolicyLayer policy for delete_connection. 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_connection? +

delete_connection is provided by the Neo4j Agent Memory MCP Server MCP server (knowall-ai/mcp-neo4j-agent-memory). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Neo4j Agent Memory MCP Server tool call.

Start from Neo4j Agent Memory 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.

9 Neo4j Agent Memory MCP 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.