Удалить тему вместе со всеми сообщениями.
AI agents call delete_forum_topic 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 deletes a forum topic and all associated messages, an action that cannot be undone. This falls clearly into the Destructive category as it causes irreversible loss of data. Severity is high because deleting an entire topic with all messages represents significant data loss, though the blast radius is limited to a single forum topic rather than the entire account.
From the tool's definition Tool name 'delete_forum_topic' and description 'Удалить тему вместе со всеми сообщениями' (Delete topic along with all messages) indicate irreversible deletion of data.
Attacks that exploit this kind of access
Удалить тему вместе со всеми сообщениями. 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_forum_topic: 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_forum_topic 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_forum_topic 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_forum_topic. 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_forum_topic 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 →