delete-prompt-entries

THE RISK

Critical Risk

Why delete-prompt-entries needs a policy

This tool irreversibly deletes data (prompt log entries) based on user-specified criteria. Deletion operations cannot be undone and represent the most severe category (Destructive). While the data affected is logs rather than primary application data, the capability to selectively purge audit/prompt history could be used to cover tracks or destroy evidence of prior LLM interactions.

From the tool's definition The tool name is 'delete-prompt-entries' and the description states it 'Delete prompt log entries matching specified criteria', using explicit deletion language that indicates irreversible data removal.

Documented attack patterns abuse exactly the kind of access delete-prompt-entries gives an agent:

POLICY

How to control delete-prompt-entries

PolicyLayer is an MCP gateway — it sits between your AI agents and Cross-LLM MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for delete-prompt-entries:

policy.json

{
  "version": "1",
  "default": "deny",
  "hide": [
    "delete-prompt-entries"
  ]
}

delete-prompt-entries 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 Cross-LLM MCP Server — 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 Cross-LLM MCP Server tools

Destructive clear-prompt-history Clear all prompt log entries Execute call-all-llms Call all available LLM APIs (ChatGPT, Claude, DeepSeek, Gemini, Grok, Kimi, Perplexity, Mi Execute call-chatgpt Call OpenAI Execute call-claude Call Anthropic Execute call-deepseek Call DeepSeek API with a prompt Execute call-gemini Call Google Execute call-grok Call xAI Execute call-huggingface Call Hugging Face Inference Router (OpenAI-compatible chat completions) with a prompt

All 23 Cross-LLM MCP Server 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 Cross-LLM MCP Server → 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-entries

What does the delete-prompt-entries tool do? +

Delete prompt log entries matching specified criteria. It is categorised as a Destructive tool in the Cross-LLM MCP 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-prompt-entries? +

Register the Cross-LLM MCP Server MCP server in PolicyLayer and add a rule for delete-prompt-entries: 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 Cross-LLM MCP Server. Nothing to install.

What risk level is delete-prompt-entries? +

delete-prompt-entries 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-entries? +

Yes. Add a rate_limit block to the delete-prompt-entries 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-entries completely? +

Set action: deny in the PolicyLayer policy for delete-prompt-entries. 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-entries? +

delete-prompt-entries is provided by the Cross-LLM MCP Server MCP server (jamesanz/cross-llm-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Cross-LLM MCP Server tool call.

Start from Cross-LLM MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →