【删除会话】当用户说
AI agents call delete_session to permanently remove resources in MCP Session Saver — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deletion operations that cannot be undone fall squarely into the Destructive category, representing the highest risk short of Financial impact. This tool would permanently remove saved AI conversation records with no recovery option, making it a critical security concern if misused by an agent without proper authorization checks.
From the tool's definition Tool name 'delete_session' explicitly indicates deletion. Description is incomplete/non-English ('【删除会话】当用户说'), but the name and function context (managing conversation records) clearly indicate irreversible data removal.
Attacks that exploit this kind of access
【删除会话】当用户说. It is categorised as a Destructive tool in the MCP Session Saver MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP Session Saver MCP server in PolicyLayer and add a rule for delete_session: 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 MCP Session Saver. Nothing to install.
delete_session 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_session 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_session. 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_session is provided by the MCP Session Saver MCP server (oscar-wang-xin/mcp-session-saver). 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 →