Delete a conversation and all its messages.
AI agents call delete_conversation to permanently remove resources in CustomGPT MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes data (a conversation and all associated messages) that cannot be recovered or undone. This is the defining characteristic of the Destructive category. The potential blast radius is high because an agent could inadvertently delete important conversation histories, user data, or communication records that may have compliance, audit, or business value.
From the tool's definition Tool name is 'delete_conversation' and description states it will 'Delete a conversation and all its messages.' The use of 'Delete' and 'all its messages' indicates irreversible removal of data.
Attacks that exploit this kind of access
Delete a conversation and all its messages. It is categorised as a Destructive tool in the CustomGPT MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the CustomGPT MCP Server 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 CustomGPT MCP Server. 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 CustomGPT MCP Server MCP server (poll-the-people/customgpt-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 →