セッションをリセット
AI agents call reset_session to permanently remove resources in MCP Claude Context Continuity — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Resetting a session implies irreversibly clearing the current session state, including conversation context and history accumulated within that session. Given this server's purpose of maintaining conversation context across multiple invocations, resetting a session would destroy that context in an unrecoverable way, placing it in the Destructive category.
From the tool's definition reset_session — 'セッションをリセット' (Reset session)
Attacks that exploit this kind of access
セッションをリセット. It is categorised as a Destructive tool in the MCP Claude Context Continuity MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP Claude Context Continuity MCP server in PolicyLayer and add a rule for reset_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 Claude Context Continuity. Nothing to install.
reset_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 reset_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 reset_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.
reset_session is provided by the MCP Claude Context Continuity MCP server (tethiro/mcp-claude-context-continuity). 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 →