Skip to main content
Glama
Sign In
mcp-abap-adt

mcp-abap-adt

by fr0ster
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

GetObjectInfo

Retrieves the object tree and structure of ABAP packages, classes, programs, and function groups by type and name, with optional node descriptions and package details for each node.

Instructions

[read-only] Returns the object tree of the package (DEVC), class (CLAS), program (PROG), function group (FUGR) or other object named by parent_type and parent_name. Shows root, group nodes, and terminal leaves up to maxDepth. With enrich=true each node also carries its description and package, from a repository search. Takes parent_type and parent_name (one object: its tree) or objects (several objects: one tree per object, in the order given; a failed one as { OBJECT_TYPE, OBJECT_NAME, error }). Read in ADT batch envelopes: per tier the root node structures of its nodes, then their type nodes; with enrich, the search of every node last. 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. Runs outside batch mode.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "GetObjectInfo"
  }
}

Input Schema

NameRequiredDescriptionDefault
enrichNo[read-only] Whether to add description and package via SearchObject (default true)
objectsNo[read-only] Several objects, read together (give this or parent_type and parent_name)
timeoutNoSeconds 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.
maxDepthNo[read-only] Maximum tree depth (default depends on type). Every object's own type folders and their contents are always shown (one tier); a higher value only descends further for PACKAGES, expanding nested subpackages that many tiers deep — no captured node-structure document shows a non-package object usefully recursable beyond its own type folders, so other object types are capped at one tier regardless of a higher value here.
parent_nameNo[read-only] Parent object name
parent_typeNo[read-only] Parent object type (e.g. DEVC/K, CLAS/OC, PROG/P); with parent_name, or give objects
include_descriptionsNo[read-only] Include each leaf's description. Where the system serves ADT batch, each description is read from the leaf's metadata: one more read per leaf, which on a large tree takes most of the call (default false)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed8 schema fields changedv20.1.0
    • addedInput schema / properties / include_descriptions
      Added value: +{
+  "default": false,
+  "description": "[read-only] Include each leaf's description. Where the system serves ADT batch, each description is read from the leaf's metadata: one more read per leaf, which on a large tree takes most of the call (default false)",
+  "type": "boolean"
+}
    • addedInput schema / properties / maxDepth / maximum
      Added value: +9007199254740991
    • addedInput schema / properties / maxDepth / minimum
      Added value: +-9007199254740991
    • changedInput schema / properties / maxDepth / type
      Previous value: -"number"New value: +"integer"
    • addedInput schema / properties / objects
      Added value: +{
+  "description": "[read-only] Several objects, read together (give this or parent_type and parent_name)",
+  "items": {
+    "properties": {
+      "object_name": {
+        "description": "Object name",
+        "type": "string"
+      },
+      "object_type": {
+        "description": "Object type (e.g. DEVC/K, CLAS/OC, PROG/P)",
+        "type": "string"
+      }
+    },
+    "required": [
+      "object_type",
+      "object_name"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}
    • changedInput schema / properties / parent_type / description
      Previous value: -"[read-only] Parent object type (e.g. DEVC/K, CLAS/OC, PROG/P)"New value: +"[read-only] Parent object type (e.g. DEVC/K, CLAS/OC, PROG/P); with parent_name, or give objects"
    • 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"
+}
    • removedInput schema / required
      Removed value: -[
-  "parent_type",
-  "parent_name"
-]
  2. Changed1 schema field changedv16.0.0
    • changedInput schema / properties / maxDepth / description
      Previous value: -"[read-only] Maximum tree depth (default depends on type)"New value: +"[read-only] Maximum tree depth (default depends on type). Every object's own type folders and their contents are always shown (one tier); a higher value only descends further for PACKAGES, expanding nested subpackages that many tiers deep — no captured node-structure document shows a non-package object usefully recursable beyond its own type folders, so other object types are capped at one tier regardless of a higher value here."
  3. First observed

TDQS

A3.6/5.0
Behavior4/5

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

With no annotations present the description carries the full burden, and it does substantial work: it discloses the dedicated ABAP session, the timeout lifecycle (read cancelled, session logged off, system unchanged), the batch-envelope ordering of tiers, that enrich triggers a repository search per node, that include_descriptions costs one extra read per leaf, and the failure shape { OBJECT_TYPE, OBJECT_NAME, error }. It stops short of stating authorization requirements or any rate/session limits, which keeps it out of the top band.

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, return shape, input modes, and timeout caveat are front-loaded, which is good. However the paragraph is dense and repeats the timeout/MCP-client-cancel warning almost word-for-word from the schema, and the trailing 'Runs outside batch mode' is orphaned from the batch discussion earlier. Several sentences could be trimmed without losing information.

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?

For a seven-parameter read tool with no annotations and no output schema, the description gives an adequate picture: what the tree contains (root, group nodes, terminal leaves), how enrich and include_descriptions change it, and how per-object failures are returned. Missing only the concrete response envelope shape and any permission expectations.

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

Parameters3/5

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

Schema coverage is 100%, so the schema already documents all seven parameters and the baseline is 3. The description does add real interpretation for maxDepth ('a higher value only descends further for PACKAGES... other object types are capped at one tier'), but its timeout and enrich text is nearly verbatim duplication of the schema descriptions, so net added meaning is modest.

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

Purpose4/5

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

Opens with a specific verb and resource: 'Returns the object tree of the package (DEVC), class (CLAS), program (PROG), function group (FUGR)', and enumerates the supported object types with their ADT codes. That is well beyond a restated name. It never distinguishes itself from close siblings such as GetObjectStructure, GetPackageTree, or GetObjectNodeFromCache, so an agent cannot tell from the description alone which of those to pick.

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

Usage Guidelines3/5

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

It clarifies the two input modes (parent_type+parent_name for one object, objects for several) and states 'Runs outside batch mode', which implies usage context. But there is no explicit when-to-use versus alternatives, no exclusions, and no prerequisite guidance despite several overlapping tree-reading siblings. Usage is inferable rather than directed.

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

Deploy Server

Other Tools