Generic ADT REST call — escape hatch for endpoints not covered by a high-level tool. Handles Basic auth, sap-client, cookies, CSRF token automatically. Path is confined to the /sap/bc/adt/ namespace.
AI agents invoke adt_request 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.
This tool makes arbitrary REST calls to SAP ADT endpoints, which can trigger reads, writes, executions, deletions, or any other operation depending on the HTTP method and path supplied. As a generic escape hatch, it subsumes all other categories. An AI agent could use it to delete objects, activate code, create transports, or perform any ADT operation.
From the tool's definition Generic ADT REST call — escape hatch for endpoints not covered by a high-level tool... Path is confined to the /sap/bc/adt/ namespace
Documented attack patterns abuse exactly the kind of access adt_request 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_request:
{
"version": "1",
"default": "deny",
"tools": {
"adt_request": {
"limits": [
{
"counter": "adt_request_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}adt_request 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.
Free to start. No card required.
Generic ADT REST call — escape hatch for endpoints not covered by a high-level tool. Handles Basic auth, sap-client, cookies, CSRF token automatically. Path is confined to the /sap/bc/adt/ namespace. 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.
Register the Claude For Abap MCP server in PolicyLayer and add a rule for adt_request: 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_request is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the adt_request 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_request. 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_request 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.