adt_set_source

THE RISK

Medium Risk

Why adt_set_source needs a policy

This tool modifies existing ABAP source code in a SAP system, which is a reversible write operation (the previous version can be recovered via version control or adt_compare_versions). It does not delete data (would be Destructive) but does create production code changes in an enterprise system, making it high severity.

From the tool's definition Tool name 'adt_set_source' and description 'Replace the ABAP source of an object' indicate modification of code artifacts in a live SAP system.

Documented attack patterns abuse exactly the kind of access adt_set_source gives an agent:

POLICY

How to control adt_set_source

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_set_source:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "adt_set_source": {
      "limits": [
        {
          "counter": "adt_set_source_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

adt_set_source stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

Create a free account and register Claude For Abap — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Claude For Abap tools

Destructive adt_delete_object Delete an ABAP object. Acquires a lock and issues DELETE. Refused under read-only mode. Execute adt_pretty_print Run the ABAP pretty printer on supplied source code (stateless — no object lookup, no lock Execute adt_run_atc Run ABAP Test Cockpit (ATC) on one or more objects. ATC endpoint shape varies across NetWe Execute adt_run_atc_package Run ABAP Test Cockpit (ATC) over an ENTIRE package via the full ADT worklist flow (create Execute adt_run_atc_transport Run ABAP Test Cockpit (ATC) over every object in a transport request via the full ADT work Execute adt_run_unit_tests Run ABAP Unit tests for one or more objects (typically test container classes). Execute adt_release_transport Release a transport request. Subject to read-only mode. Execute adt_request Generic ADT REST call — escape hatch for endpoints not covered by a high-level tool. Handl

All 45 Claude For Abap tools →

Write tools on other servers

M-Team MCP Server download_torrent YouTube MCP Server generate_video_title Android Forensics ADB MCP Server combine_reports 0xarchive web3_signup

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Argument validation → Checking tool call arguments against schema and policy before they run.
Scoped token → Per-person credentials that grant a defined subset of servers and tools.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about adt_set_source

What does the adt_set_source tool do? +

Replace the ABAP source of an object. The supplied. It is categorised as a Write tool in the Claude For Abap MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on adt_set_source? +

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

adt_set_source is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit adt_set_source? +

Yes. Add a rate_limit block to the adt_set_source 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_set_source completely? +

Set action: deny in the PolicyLayer policy for adt_set_source. 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_set_source? +

adt_set_source 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.

Enforce policy on every Claude For Abap tool call.

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.

CHECK YOUR STACK →