Reset your context back to a saved checkpoint, injecting a handoff message to your future self. The message_to_self will appear as if you wrote it just before the reset. Use it to brief your future self on: - What was accomplished since the checkpoint - Key findings and decisions - Clear next ste...
AI agents call reset_to_checkpoint to permanently remove resources in Context Travel MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Resetting to a checkpoint overwrites and discards the current context state in a way that cannot be undone (the intervening context is lost). While checkpoints can be saved beforehand, the reset itself is a one-way destructive operation on the current context window. This places it firmly in the Destructive category.
From the tool's definition Reset your context back to a saved checkpoint — context will be restored to the checkpoint state, irreversibly discarding all context state accumulated since that checkpoint
Attacks that exploit this kind of access
Reset your context back to a saved checkpoint, injecting a handoff message to your future self. The message_to_self will appear as if you wrote it just before the reset. Use it to brief your future self on: - What was accomplished since the checkpoint - Key findings and decisions - Clear next steps - Critical details (file paths, variable names, gotchas) After calling this, your context will be restored to the checkpoint state plus your handoff message. It is categorised as a Destructive tool in the Context Travel MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Context Travel MCP server in PolicyLayer and add a rule for reset_to_checkpoint: 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 Context Travel MCP. Nothing to install.
reset_to_checkpoint 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_to_checkpoint 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_to_checkpoint. 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_to_checkpoint is provided by the Context Travel MCP server (simen/mcp-memento). 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 →