Creates an empty checkpoint with the given ID.
AI agents use create_checkpoint to create or update resources in Kustomize MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Kustomize MCP environment.
This tool performs a reversible state creation operation within the Kustomize configuration analysis workflow. Creating an empty checkpoint is a Write action because it modifies data (adds a new checkpoint record) without irreversibly deleting or overwriting existing data.
From the tool's definition Tool creates a new checkpoint (empty state), which is reversible and has no destructive side effects. The description explicitly states 'Creates an empty checkpoint with the given ID,' indicating a write operation that modifies checkpointing state.
Attacks that exploit this kind of access
Creates an empty checkpoint with the given ID. It is categorised as a Write tool in the Kustomize MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Kustomize MCP server in PolicyLayer and add a rule for create_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.
create_checkpoint is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_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 create_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.
create_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 →