rollback_session
Rollback all changes made in the current AI session
This record as markdown: /tools/agentics-ai-code-mcp/rollback-session.md
What rollback_session does on Code MCP Server
AI agents call rollback_session to permanently remove resources in Code MCP Server, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Why rollback_session is rated Critical
Rolling back all session changes is an irreversible bulk undo operation that discards all modifications made during the session. Unlike a simple 'undo' in an editor, this operates at the session level and likely cannot be re-applied, making it destructive. Misuse by an AI agent could silently discard legitimate work across an entire session.
From the tool's definition Rollback all changes made in the current AI session
Attacks that exploit this kind of access
The rule that runs rollback_session safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Code MCP Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For rollback_session, this is the rule to start with:
rollback_session is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect Code MCP Server, apply this rule, and every rollback_session call is checked against it from then on.
Questions about rollback_session
Rollback all changes made in the current AI session. It is categorised as a Destructive tool in the Code MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Code MCP Server MCP server in PolicyLayer and add a rule for rollback_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 Code MCP Server. Nothing to install.
rollback_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 rollback_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 rollback_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.
rollback_session is provided by the Code MCP Server MCP server (agentics-ai/code-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Code MCP Server, and thousands of servers like it.
Across the catalogue