End the debug session: delete this process
AI agents call adt_debug_stop to permanently remove resources in Claude For Abap — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool explicitly deletes a process to end the debug session. Deleting a running process is irreversible — the process is terminated and cannot be resumed. This constitutes a destructive action with a high blast radius if misused, as it could terminate critical SAP system processes or active debug sessions unexpectedly.
From the tool's definition End the debug session: delete this process
Attacks that exploit this kind of access
End the debug session: delete this process. It is categorised as a Destructive tool in the Claude For Abap MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Claude For Abap MCP server in PolicyLayer and add a rule for adt_debug_stop: 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 Claude For Abap. Nothing to install.
adt_debug_stop 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 adt_debug_stop 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 adt_debug_stop. 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.
adt_debug_stop is provided by the Claude For Abap MCP server (yzonur/claude-for-abap). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
adt_debug_stop is one line of Claude For Abap's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →