Очистить draft в чате (синхронизация на все устройства).
AI agents call clear_draft 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.
Clearing a draft irreversibly removes unsaved message content and syncs the deletion across all user devices, making recovery unlikely. This is a destructive action with medium severity since it affects draft content rather than sent messages or critical data.
From the tool's definition Очистить draft в чате (синхронизация на все устройства) — 'Очистить' means 'Clear/Delete', removing the draft message across all devices
Attacks that exploit this kind of access
Очистить draft в чате (синхронизация на все устройства). 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 clear_draft: 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.
clear_draft 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 clear_draft 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 clear_draft. 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.
clear_draft 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.
clear_draft is one line of Claudegram's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →