Critical Risk →

delete_memory

Delete a memory and all its relationships

How to control delete_memory ↓

What delete_memory does on Claude Code Memory Server

AI agents call delete_memory to permanently remove resources in Claude Code 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_memory needs a policy

This tool permanently removes stored memories and their graph relationships without any undo capability. While the data domain (development task memories) is not critical infrastructure, the destructive nature of the operation and potential loss of important context, patterns, or solutions across sessions justifies 'Destructive' classification and 'high' severity.

From the tool's definition Tool name is 'delete_memory' with description 'Delete a memory and all its relationships' - explicitly irreversible deletion operation that removes data from the Neo4j graph database.

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

How to control delete_memory

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

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

delete_memory 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 Claude Code 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_memory

What does the delete_memory tool do? +

Delete a memory and all its relationships. It is categorised as a Destructive tool in the Claude Code 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_memory? +

Register the Claude Code Memory Server MCP server in PolicyLayer and add a rule for delete_memory: 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 Claude Code Memory Server. Nothing to install.

What risk level is delete_memory? +

delete_memory 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_memory? +

Yes. Add a rate_limit block to the delete_memory 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_memory completely? +

Set action: deny in the PolicyLayer policy for delete_memory. 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_memory? +

delete_memory is provided by the Claude Code Memory Server MCP server (viralv00d00/claude-code-memory). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Claude Code Memory Server tool call.

Start from Claude Code 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 Claude Code 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.