Clears all checkpoints or a specific checkpoint if an ID is provided.
AI agents call clear_checkpoint to permanently remove resources in Kustomize MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Checkpoint clearing removes stored state/snapshots that are part of the checkpointing system described in the server's purpose. This is irreversible data deletion with potential blast radius if an AI agent mistakenly clears checkpoints needed for configuration management or audit trails.
From the tool's definition Tool description explicitly states 'Clears all checkpoints or a specific checkpoint' — the word 'clears' indicates irreversible deletion of data. This is a destructive operation that cannot be undone.
Attacks that exploit this kind of access
Clears all checkpoints or a specific checkpoint if an ID is provided. It is categorised as a Destructive tool in the Kustomize MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Kustomize MCP server in PolicyLayer and add a rule for clear_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 Kustomize MCP. Nothing to install.
clear_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 clear_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 clear_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.
clear_checkpoint is provided by the Kustomize MCP server (mbrt/kustomize-mcp). 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 →