delete_prompt

THE RISK

Critical Risk

Why delete_prompt needs a policy

This tool permanently removes data (a prompt template) that cannot be recovered unless backed up externally. While the blast radius is contained to prompt templates rather than production data, deletion is inherently destructive. The fallback to global defaults does not undo the deletion itself.

From the tool's definition Tool name is 'delete_prompt' and description states it 'Deletes a prompt from the project-specific directory.' The verb 'deletes' combined with removal from storage indicates an irreversible deletion operation.

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

POLICY

How to control delete_prompt

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

policy.json

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

delete_prompt 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 Prompt Registry MCP — 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 Prompt Registry MCP tools

Write load_default_prompts Loads all default prompts from the default_prompts_data directory into the active prompt d Write add_prompt Adds a new prompt to the project-specific prompt directory. Write refine_and_add_prompt Optimizes a prompt using Claude Prompt Optimizer techniques, then adds the refined version Write update_prompt Updates an existing prompt. Updates are always written to the project-specific directory, Read filter_prompts_by_tags Lists active prompts (project-specific or user global defaults) that match all specified t Read get_prompt_file_content Retrieves the raw JSON definition of the active prompt (project-specific or user global de

All 7 Prompt Registry MCP 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 Prompt Registry MCP → 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_prompt

What does the delete_prompt tool do? +

Deletes a prompt from the project-specific directory. If a user global default with the same ID exists, it will become active. It is categorised as a Destructive tool in the Prompt Registry MCP 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_prompt? +

Register the Prompt Registry MCP server in PolicyLayer and add a rule for delete_prompt: 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 Prompt Registry MCP. Nothing to install.

What risk level is delete_prompt? +

delete_prompt 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_prompt? +

Yes. Add a rate_limit block to the delete_prompt 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_prompt completely? +

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

delete_prompt is provided by the Prompt Registry MCP server (stevengonsalvez/promptregistry-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Prompt Registry MCP tool call.

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

CHECK YOUR STACK →