// MCP TOOL REFERENCE

memory_delete

Delete a memory that is outdated, incorrect, or superseded. Prefer updating (delete + add) over keeping stale memories. You can only delete memories created by your token.

ServerShellgate
CategoryDestructive

How to control memory_delete ↓

WHAT IT DOES

What memory_delete does on Shellgate

AI agents call memory_delete to permanently remove resources in Shellgate — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.

THE RISK

Critical Risk

Why memory_delete needs a policy

This tool permanently removes stored data (memories/context) without recovery option. While scoped to memories created by the agent's token, deletion of persistent state is irreversible and constitutes a destructive action.

From the tool's definition Tool name is 'memory_delete' and description explicitly states 'Delete a memory'. The description confirms irreversible deletion: 'Delete a memory that is outdated, incorrect, or superseded' with preference to 'delete + add' over retention.

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

POLICY

How to control memory_delete

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

policy.json

{
  "version": "1",
  "default": "deny",
  "hide": [
    "memory_delete"
  ]
}

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

Create a free account and register Shellgate — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RESTRICT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Shellgate tools

Destructive org_skill_delete Delete a shared organization skill from Shellgate Destructive wiki_delete_page Archive a wiki page (soft delete). Sets status to Execute ssh_exec Execute a command on an SSH target. If the response has status Execute api_request Proxy an HTTP request through the gateway to an upstream API target. If the response has s Execute blind_type Type a sensitive vault field value using keyboard events. The target field must be focused Write webhook_ack Acknowledge processed webhook events Write blind_fill Fill a sensitive vault field into a browser element via CSS selector. The secret never app Write mail_draft Create a draft email in the Drafts folder.

All 31 Shellgate tools →

Destructive tools on other servers

Android Forensics ADB MCP Server create_full_backup 0xarchive web3_revoke_key Frida Game Hacking MCP clear_scan cPanel MCP Server clear_spam_box

Go deeper

Critical-risk tools in Shellgate → Every critical-risk tool this server exposes, in one view.
All critical-risk MCP tools → Every critical-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Blast radius → How much damage one compromised or confused agent can do — and how to bound it.
Tool call approval → Approval gates on individual tool calls: auto-allow, prompt, or deny.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about memory_delete

What does the memory_delete tool do? +

Delete a memory that is outdated, incorrect, or superseded. Prefer updating (delete + add) over keeping stale memories. You can only delete memories created by your token. It is categorised as a Destructive tool in the Shellgate 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 memory_delete? +

Register the Shellgate MCP server in PolicyLayer and add a rule for memory_delete: 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 Shellgate. Nothing to install.

What risk level is memory_delete? +

memory_delete 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 memory_delete? +

Yes. Add a rate_limit block to the memory_delete 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 memory_delete completely? +

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

memory_delete is provided by the Shellgate MCP server (matthiastjong/shellgate). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Shellgate tool call.

Start from Shellgate, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →

Free to start. No card required.

31 Shellgate tools catalogued and risk-classified — across an index of 43,000+ MCP servers.