Low Risk

adt_grep_source

Full-text regex search across ABAP source. Complements adt_search_objects (which only matches names). Scope the search to a package (optionally recursive), a transport request, or an explicit object list. Fetches /source/main for each source-bearing object (programs, classes, interfaces, includes...

How to control adt_grep_source ↓

What adt_grep_source does on Claude For Abap

AI agents call adt_grep_source 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.

Low Risk

Why adt_grep_source needs a policy

adt_grep_source is purely a retrieval and search operation. It queries ABAP source code and returns matching results without any side effects or state changes. While it provides access to SAP system code (which could be sensitive information), the action itself is read-only.

From the tool's definition Tool performs 'full-text regex search across ABAP source' and 'returns matching lines as object + line + text'. It 'fetches /source/main' and retrieves data without modification.

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

How to control adt_grep_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_grep_source:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "adt_grep_source": {}
  }
}

adt_grep_source is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

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

Free to start. No card required.

Related tools and policies

Go deeper

Questions about adt_grep_source

What does the adt_grep_source tool do? +

Full-text regex search across ABAP source. Complements adt_search_objects (which only matches names). Scope the search to a package (optionally recursive), a transport request, or an explicit object list. Fetches /source/main for each source-bearing object (programs, classes, interfaces, includes, CDS/DDLS, DCLS, DDLX, behavior definitions) and returns matching lines as object + line + text. DDIC primitives (tables, data elements, domains) and function groups are skipped (no single source document). Bounded by maxObjects and maxMatches — large packages are truncated, not silently capped. It is categorised as a Read tool in the Claude For Abap MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on adt_grep_source? +

Register the Claude For Abap MCP server in PolicyLayer and add a rule for adt_grep_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_grep_source? +

adt_grep_source is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit adt_grep_source? +

Yes. Add a rate_limit block to the adt_grep_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_grep_source completely? +

Set action: deny in the PolicyLayer policy for adt_grep_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_grep_source? +

adt_grep_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.

Free to start. No card required.

45 Claude For Abap tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.