AI agents call remove_memory_shell to permanently remove resources in Memory Shell Detector MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool performs irreversible removal of code from memory, which cannot be undone without restarting the process or restoring from backups. This is a destructive operation with high blast radius if misapplied—an AI agent could permanently remove legitimate or critical code.
From the tool's definition Tool name 'remove_memory_shell' combined with server description stating it 'safely remove[s] memory shells after user confirmation' indicates irreversible deletion of detected malicious code from running Java processes.
Documented attack patterns abuse exactly the kind of access remove_memory_shell gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Memory Shell Detector MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for remove_memory_shell:
{
"version": "1",
"default": "deny",
"hide": [
"remove_memory_shell"
]
}remove_memory_shell disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
remove_memory_shell. It is categorised as a Destructive tool in the Memory Shell Detector MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Memory Shell Detector MCP server in PolicyLayer and add a rule for remove_memory_shell: 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 Memory Shell Detector MCP. Nothing to install.
remove_memory_shell 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 remove_memory_shell 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 remove_memory_shell. 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.
remove_memory_shell is provided by the Memory Shell Detector MCP server (ruoji6/memory-shell-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Memory Shell Detector MCP, 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 Memory Shell Detector MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.