adt_debug_set_watchpoint · Claude For Abap MCP

WHAT IT DOES

What adt_debug_set_watchpoint does on Claude For Abap

AI agents invoke adt_debug_set_watchpoint 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_set_watchpoint needs a policy

Setting a debugger watchpoint triggers active debugger intervention in a live SAP/ABAP system — it causes the system to halt execution when conditions are met, affecting running processes. This is an Execute-category action (triggering external operations on a live system). It's not purely Write (data creation/modification) nor Destructive, but it does interact with and can disrupt live system execution.

From the tool's definition 'Set a debugger watchpoint that breaks when a variable changes (or a condition holds)' and 'Phase 3, WRITE — refused under read-only mode'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

adt_debug_set_watchpoint Rate-limited

adt_debug_set_watchpoint 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_set_watchpoint": {
      "limits": [
        {
          "counter": "adt_debug_set_watchpoint_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_set_watchpoint

What does the adt_debug_set_watchpoint tool do? +

Set a debugger watchpoint that breaks when a variable changes (or a condition holds). Phase 3, WRITE — refused under read-only mode. NOTE: the watchpoint request/response contract has no reference implementation and is best-effort until validated on a live system; check. 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_set_watchpoint? +

Register the Claude For Abap MCP server in PolicyLayer and add a rule for adt_debug_set_watchpoint: 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_set_watchpoint? +

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

Can I rate-limit adt_debug_set_watchpoint? +

Yes. Add a rate_limit block to the adt_debug_set_watchpoint 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_set_watchpoint completely? +

Set action: deny in the PolicyLayer policy for adt_debug_set_watchpoint. 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_set_watchpoint? +

adt_debug_set_watchpoint 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.