Забанить участника навсегда — он не сможет вернуться.
AI agents call ban_participant 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 bans a participant from a chat/channel with no way to undo or return. The explicit 'навсегда' (permanently) and 'не сможет вернуться' (cannot return) indicate an irreversible action, classifying it as Destructive. High severity because misuse could permanently remove users from communities.
From the tool's definition Забанить участника навсегда — он не сможет вернуться (Ban participant permanently — they cannot return)
Attacks that exploit this kind of access
Забанить участника навсегда — он не сможет вернуться. 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 ban_participant: 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.
ban_participant 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 ban_participant 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 ban_participant. 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.
ban_participant 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 →