Delete a checkpoint to free resources. Each checkpoint consumes memory
AI agents call checkpoint_delete to permanently remove resources in Rr — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting checkpoints removes saved execution states that cannot be recovered. While the impact is scoped to debugging artifacts rather than production data, the action is irreversible and fits the Destructive category (irreversibly deletes data). Severity is high because loss of checkpoints could impede debugging workflow and analysis, though it does not affect production systems or have broader blast radius.
From the tool's definition Tool name: 'checkpoint_delete' with description: 'Delete a checkpoint to free resources.' The verb 'Delete' and action of removing checkpoints (which represent saved debugging states) indicates irreversible data removal.
Attacks that exploit this kind of access
Delete a checkpoint to free resources. Each checkpoint consumes memory. It is categorised as a Destructive tool in the Rr MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Rr MCP server in PolicyLayer and add a rule for checkpoint_delete: 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 Rr. Nothing to install.
checkpoint_delete 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 checkpoint_delete 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 checkpoint_delete. 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.
checkpoint_delete is provided by the Rr MCP server (jnjaeschke/rr-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 →