adt_debug_listen · Claude For Abap MCP: Risk & Policy

WHAT IT DOES

What adt_debug_listen does on Claude For Abap

AI agents invoke adt_debug_listen to trigger actions in Claude For Abap. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why adt_debug_listen needs a policy

This tool enables an AI agent to attach to and control the execution flow of live SAP ABAP processes by listening for and intercepting breakpoints. While not directly destructive or financial, it permits arbitrary inspection and potential manipulation of running code execution in a mission-critical enterprise system.

From the tool's definition Tool name 'adt_debug_listen' and description explicitly states it 'Wait[s]...for a debuggee to hit a breakpoint' and 'auto-attaches' when a session is trapped. This is a debugger attachment mechanism that gains control of running ABAP processes.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

adt_debug_listen Rate-limited

adt_debug_listen stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "adt_debug_listen": {
      "limits": [
        {
          "counter": "adt_debug_listen_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Claude For Abap, so you can run agents against it safely.

FAQ

Questions about adt_debug_listen

What does the adt_debug_listen tool do? +

Wait (bounded long-poll) for a debuggee to hit a breakpoint set with adt_debug_set_breakpoint. Returns { caught: true, … } with a summary (and auto-attaches) when a session is trapped, or { caught: false } if none arrived within the timeout — in which case call it again (trigger the ABAP run meanwhile). One listener per process; set breakpoints first. It is categorised as a Execute tool in the Claude For Abap MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on adt_debug_listen? +

Register the Claude For Abap MCP server in PolicyLayer and add a rule for adt_debug_listen: 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.

What risk level is adt_debug_listen? +

adt_debug_listen is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit adt_debug_listen? +

Yes. Add a rate_limit block to the adt_debug_listen 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.

How do I block adt_debug_listen completely? +

Set action: deny in the PolicyLayer policy for adt_debug_listen. 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.

What MCP server provides adt_debug_listen? +

adt_debug_listen 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.