Покинуть чат/канал или удалить личный диалог.
AI agents call delete_dialog 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 permanently removes dialogs/conversations from a Telegram account. Deletion of chat history cannot be undone and represents an irreversible loss of data. While leaving a chat is technically reversible (re-joining), the 'delete' aspect targets permanent removal.
From the tool's definition Tool name 'delete_dialog' combined with description 'Покинуть чат/канал или удалить личный диалог' (Leave chat/channel or delete personal dialog) indicates irreversible deletion of conversation history and data.
Attacks that exploit this kind of access
Покинуть чат/канал или удалить личный диалог. 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_dialog: 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_dialog 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_dialog 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_dialog. 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_dialog 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 →