delete_dialogs
AI agents call delete_dialogs to permanently remove resources in Claudegram — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly deletes Telegram dialogs/conversations. Deletion cannot be undone, placing it in the Destructive category. The high severity reflects that an AI agent could lose user data permanently if misused. Confidence is high despite the empty description because 'delete' is unambiguously destructive in this context, and the Telegram domain confirms dialogs are user data.
From the tool's definition Tool name is 'delete_dialogs' with an empty description. The verb 'delete' combined with 'dialogs' (conversations/chats in Telegram) indicates irreversible deletion of data.
Attacks that exploit this kind of access
delete_dialogs. It is categorised as a Destructive tool in the Claudegram MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Claudegram MCP server in PolicyLayer and add a rule for delete_dialogs: 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 Claudegram. Nothing to install.
delete_dialogs 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_dialogs 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_dialogs. 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_dialogs is provided by the Claudegram MCP server (sanjar-x/claudegram). 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 →