mcp-abap-adt

SearchObject

Search the ABAP repository by object name or wildcard pattern, optionally filtering by object type, to find, verify, or list matching development objects.

Instructions

[read-only] Search ABAP repository by object name or wildcard pattern (e.g. 'Z*'). Answers: "find object X", "does X exist", "list objects matching...", "search for program/class/table by name". Supports all repository object types — optionally filter by type (PROG, CLAS, INTF, DEVC, TABL, DDLS, DTEL, FUGR, SRVD, SRVB, BDEF, DDLX, etc.). Runs on an ABAP session of its own. Optional timeout (seconds): when it passes, the read is cancelled, its ABAP session logged off, and the system stays as it was. Set it below your MCP client's request limit — the TypeScript SDK's client cancels at 60 s; a client's cancel ends only the client's wait, and SAP runs the read on. Recordable: in batch mode a call is recorded under the next number and answers with empty content; its answer is read by number after the batch ends.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "object_name": "<object_name>"
    },
    "name": "SearchObject"
  }
}

Input Schema

Name	Required	Description	Default
`detail`	No	How much of the answer to return: "terse" (default, the fields you need to act), "full" (the whole parse), "raw" (the document as ADT sent it).	terse
`timeout`	No	Seconds to wait for the answer: a whole number, at least 1, no default — without it the call waits until SAP answers. When it passes, the read is cancelled (its ABAP session is logged off) and the call answers that nothing was changed. Set it below your MCP client's request limit — the TypeScript SDK's client cancels at 60 s; a cancel does nothing to SAP.
`maxResults`	No	[read-only] Maximum number of results to return
`object_name`	Yes	[read-only] Object name or mask (e.g. 'MARA*')
`object_type`	No	[read-only] Optional ABAP object type (e.g. 'TABL', 'CLAS/OC')

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv20.1.0Oct 24, 2026

addedInput schema / properties / timeout

Added value: +{
+  "description": "Seconds to wait for the answer: a whole number, at least 1, no default — without it the call waits until SAP answers. When it passes, the read is cancelled (its ABAP session is logged off) and the call answers that nothing was changed. Set it below your MCP client's request limit — the TypeScript SDK's client cancels at 60 s; a cancel does nothing to SAP.",
+  "maximum": 2147483,
+  "minimum": 1,
+  "type": "integer"
+}

Changed1 schema field changedv16.0.0Oct 4, 2026

addedInput schema / properties / detail

Added value: +{
+  "default": "terse",
+  "description": "How much of the answer to return: \"terse\" (default, the fields you need to act), \"full\" (the whole parse), \"raw\" (the document as ADT sent it).",
+  "enum": [
+    "terse",
+    "full",
+    "raw"
+  ],
+  "type": "string"
+}

First observedDec 29, 2025

TDQS

A4.4/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are supplied, so the description carries the full burden and does: it declares read-only behavior, discloses that it 'runs on an ABAP session of its own', and explains timeout semantics precisely — the read is cancelled, the session is logged off, and the system is left unchanged. It also warns that a client-side cancel only ends the client's wait while SAP keeps running, and explains batch-mode recording with empty content, which are exactly the non-obvious traits an agent must know before calling.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose is correctly front-loaded and the quoted intents are efficient, but the timeout paragraph largely restates the schema's own timeout description, including the 60s TypeScript SDK note, which appears in both places. The final batch-mode sentence is information-dense but crammed into one long line, costing readability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and no annotations, the description does substantial work: session isolation, cancellation semantics, and batch-mode return behavior are all covered. What it leaves out is the shape of a normal successful answer — whether results are names, object URIs, or typed entries — and how maxResults interacts with truncation, which an agent sorting through 100+ matches would want.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so a 3 is the floor, but the description adds real meaning the schema lacks: it enumerates the supported object types (PROG, CLAS, INTF, DEVC, TABL, DDLS, DTEL, FUGR, SRVD, SRVB, BDEF, DDLX) rather than the schema's two examples, and shows the wildcard mask form. It says nothing about maxResults beyond the schema's terse 'maximum number of results', leaving result truncation behavior implicit.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Search ABAP repository by object name or wildcard pattern') and immediately scopes it to name-based lookup, which separates it from source-level siblings like SearchSource and typed enumerations like GetObjectsByType. The quoted user intents ('find object X', 'does X exist', 'list objects matching...') make the retrieval scope unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The intent phrases ('find object X', 'does X exist', 'list objects matching...') give a clear picture of when to reach for this tool, including the existence-check case that many searchers handle poorly. It does not name an alternative or state when not to use it (e.g. when to prefer SearchSource for a text grep), so it stops short of full routing guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server