Завершить чужую активную сессию по hash из get_authorizations.
AI agents call terminate_authorization 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.
Terminating an authorization session is an irreversible destructive action — once a session is killed, it cannot be undone. Misuse could lock users out of their accounts or disrupt active sessions. The tool takes a session hash from get_authorizations and permanently ends that session.
From the tool's definition Завершить чужую активную сессию — 'terminate' an active session, which is an irreversible action (the session is destroyed and cannot be restored)
Attacks that exploit this kind of access
Завершить чужую активную сессию по hash из get_authorizations. 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 terminate_authorization: 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.
terminate_authorization 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 terminate_authorization 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 terminate_authorization. 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.
terminate_authorization 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 →