Permanently delete EVERY regular ChatGPT conversation. Requires confirm=True.
AI agents call delete_all_conversations to permanently remove resources in Codex Chats — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly deletes all user conversations without targeting specific items. The destructive action is confirmed by the permanent nature (cannot be undone), the scope (all conversations), and the confirmation requirement (indicates high-risk operation). This is the most severe category applicable.
From the tool's definition Tool description explicitly states "Permanently delete EVERY regular ChatGPT conversation" — uses "Permanently delete" and "EVERY", indicating irreversible bulk data destruction.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Permanently delete EVERY regular ChatGPT conversation. Requires confirm=True. It is categorised as a Destructive tool in the Codex Chats MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Codex Chats MCP server in PolicyLayer and add a rule for delete_all_conversations: 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 Codex Chats. Nothing to install.
delete_all_conversations 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 delete_all_conversations 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 delete_all_conversations. 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.
delete_all_conversations is provided by the Codex Chats MCP server (shoyu-ramen/codex-chats-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →