List ABAP short dumps (ST22) from the runtime-dumps Atom feed. Each entry exposes id, runtime error name, terminated program, timestamp, user, and any release-specific rba:*/dump:* fields surfaced by the system. The server-side row cap is unreliable across releases (some ignore it) — adt_list_dum...
AI agents call adt_list_dumps to retrieve information from Claude For Abap without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries runtime dump information from SAP systems via the ST22 feed. It has no side effects on data — it only reads diagnostic logs. While the information exposed (error details, user identifiers, program names) could be sensitive in a security context, the tool itself performs only read operations.
From the tool's definition Tool name 'adt_list_dumps' and description state it 'List[s] ABAP short dumps' and 'exposes id, runtime error name, terminated program, timestamp, user' — pure retrieval of diagnostic data with no modification or deletion.
Documented attack patterns abuse exactly the kind of access adt_list_dumps gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Claude For Abap, and nothing reaches the server without passing your rules. This is the rule we recommend for adt_list_dumps:
{
"version": "1",
"default": "deny",
"tools": {
"adt_list_dumps": {}
}
}adt_list_dumps is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
List ABAP short dumps (ST22) from the runtime-dumps Atom feed. Each entry exposes id, runtime error name, terminated program, timestamp, user, and any release-specific rba:*/dump:* fields surfaced by the system. The server-side row cap is unreliable across releases (some ignore it) — adt_list_dumps trims to maxResults on the client too. Use adt_get_dump with an id for the full dump text. It is categorised as a Read tool in the Claude For Abap MCP Server, which means it retrieves data without modifying state.
Register the Claude For Abap MCP server in PolicyLayer and add a rule for adt_list_dumps: 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_list_dumps is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the adt_list_dumps 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_list_dumps. 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_list_dumps 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.
Start from Claude For Abap, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
45 Claude For Abap tools catalogued and risk-classified — across an index of 43,000+ MCP servers.