Delete a breakpoint permanently. Get breakpoint_id
AI agents call breakpoint_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.
This is a destructive operation because it permanently deletes debugging state. Although the impact is scoped to a debugging session rather than production data, deletion of breakpoints is irreversible and represents loss of configuration state. An agent misusing this tool could remove all breakpoints, severely impairing visibility into program execution during debugging.
From the tool's definition 'Delete a breakpoint permanently' — the tool irreversibly removes debugger breakpoints, which cannot be undone without re-creating them
Attacks that exploit this kind of access
Delete a breakpoint permanently. Get breakpoint_id. 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 breakpoint_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.
breakpoint_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 breakpoint_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 breakpoint_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.
breakpoint_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 →