Permanently delete a regular ChatGPT conversation by ID.
AI agents call delete_conversation 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 removes data (ChatGPT conversations) and cannot be undone, fitting the Destructive category. Severity is high because accidental or malicious deletion of conversations could result in loss of important chat history and context, affecting user data integrity. Confidence is high given explicit language about permanent deletion.
From the tool's definition Tool name is 'delete_conversation' with description stating 'Permanently delete a regular ChatGPT conversation by ID.' The word 'Permanently' indicates irreversible deletion with no undo capability.
Attacks that exploit this kind of access
Permanently delete a regular ChatGPT conversation by ID. 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_conversation: 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_conversation 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_conversation 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_conversation. 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_conversation 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 →