clear_session
AI agents call clear_session to permanently remove resources in MCP AI Agent Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Session data (history, state, preferences) is typically important and non-recoverable once cleared. This action cannot be undone without restoring from backups. While not as critical as deleting user accounts or permanent data stores, clearing an active session represents an irreversible operation that could disrupt ongoing work.
From the tool's definition Tool name 'clear_session' combined with the server's session management context indicates irreversible deletion or clearing of session data.
Attacks that exploit this kind of access
clear_session. It is categorised as a Destructive tool in the MCP AI Agent Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP AI Agent Server MCP server in PolicyLayer and add a rule for clear_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 AI Agent Server. Nothing to install.
clear_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 clear_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 clear_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.
clear_session is provided by the MCP AI Agent Server MCP server (singularitybridge/mcp-ai-agent-server). 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 →