delete_item

THE RISK

Critical Risk

Why delete_item needs a policy

This tool irreversibly removes configuration data from Claude Code's scope hierarchy. Once deleted, items cannot be recovered without external backups. While the blast radius is somewhat constrained to configuration management (not system-wide destruction), the permanent nature of deletion and the criticality of configuration integrity in a code organization system justify 'high' severity.

From the tool's definition Tool name is 'delete_item' and description states 'Delete a ${harnessName} configuration item.' The verb 'delete' combined with the action of removing configuration items indicates irreversible data destruction.

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

POLICY

How to control delete_item

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

policy.json

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

delete_item 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 Claude Code Organizer — 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 Claude Code Organizer tools

Write move_item Move a ${harnessName} configuration item from one scope to another. Run scan_inventory fir Read audit_security Scan all MCP servers for security vulnerabilities. Connects to each server, retrieves tool Read list_destinations List valid destination scopes for a specific item. Shows where this item can be moved to. Read scan_inventory Scan all ${harnessName} configurations across ${scopeList} scopes. Returns ${categoryList}

All 5 Claude Code Organizer 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 Claude Code Organizer → 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 delete_item

What does the delete_item tool do? +

Delete a ${harnessName} configuration item. Run scan_inventory first to see available items and scope IDs. It is categorised as a Destructive tool in the Claude Code Organizer 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_item? +

Register the Claude Code Organizer MCP server in PolicyLayer and add a rule for delete_item: 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 Organizer. Nothing to install.

What risk level is delete_item? +

delete_item 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_item? +

Yes. Add a rate_limit block to the delete_item 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_item completely? +

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

delete_item is provided by the Claude Code Organizer MCP server (mcpware/cross-code-organizer). 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 Organizer tool call.

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

CHECK YOUR STACK →