abap-mcp

Overview Schema Source Related Servers Discussions Admin

Check ABAP Cloud readiness

check_cloud_readiness

Read-onlyIdempotent

Assess ABAP source for ABAP Cloud readiness by diffing classic vs Cloud parser findings to flag migration blockers, tech-debt grade, and released-API observations.

Instructions

Assess how far ABAP source is from ABAP Cloud (Clean Core tier 1) by parsing it twice — once at a classic baseline (default v758) and once at version Cloud — and diffing: findings that appear only at Cloud are genuine cloud blockers (statements ABAP Cloud removed), reported in categories (dynpro, list output, native SQL, report events, …) with a transparent score, an A–D tech-debt grade and a verdict; findings already present at the baseline are reported separately as broken code, not migration work. It also reports snapshot-dated released-API observations for direct table and function-module references the parser can extract; those stay separate from the language-level blocker count and score. Use this when someone asks 'is this code cloud-ready / Clean Core compliant / S/4HANA-cloud safe', before porting classic ABAP into an ABAP Cloud environment, or for a graded tech-debt assessment of an abapGit export. It is static and parser-level: its released-API scan is not exhaustive dependency discovery, it does not connect to any SAP system or run ATC, and a 'ready' verdict means no detected language-level blockers — not a certification. Our A–D grade is blocker density (see gradeMeaning), NOT SAP's own Clean Core Level A–D; a target system's own released-API ATC check ("Usage of Released APIs (Cloudification Repository)" for SAP Cloud ERP Public Edition / "Usage of APIs (Cloudification Repository)" for SAP Cloud ERP Private Edition / on-premise, via variants such as ABAP_CLEAN_CORE_DEVELOPMENT / ABAP_CLEAN_CORE_READINESS) remains authoritative. Example: check_cloud_readiness({ "files": [ { "source": "REPORT zold.\nWRITE: / 'hi'." } ] }).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`files`	Yes	Source files to analyze, up to 32 per call, 100k chars each.
`edition`	No	SAP edition of the bundled Cloudification snapshot to check against: "s4hc" (default, SAP Cloud ERP Public Edition), "btp" (SAP BTP ABAP environment), or "pce" (SAP Cloud ERP Private Edition / on-premise). Release state and successors can differ by edition — the same object may be released in one and not yet in another.	s4hc
`baselineVersion`	No	Classic ABAP version the code is assumed to run on today; used to separate broken-anyway code from cloud blockers.	v758

Output Schema

TableJSON Schema

Name	Required	Description
`grade`	Yes	Blocker-density tech-debt grade (see gradeMeaning): A = no blockers, B = ≤ 0.5 blockers/file, C = ≤ 2 blockers/file, D = more. The same objective count as the score, sized for assessment reports.
`score`	Yes	100 − 5×blockers, floored at 0. Transparent, not an oracle.
`edition`	Yes	SAP edition the released-API findings were checked against.
`verdict`	Yes	Banded verdict from the blocker count (0 / ≤5 / ≤20 / >20).
`fileCount`	Yes	Files analyzed — the denominator of the grade's density banding.
`scopeNote`	Yes	Exactly what this check does and does not cover.
`categories`	Yes
`gradeMeaning`	Yes	What `grade` means: a banding of blockers per file. NOT SAP's own Clean Core Level A–D (see cleanCoreVocabulary.cleanCoreLevels for those) — do not conflate the two.
`baselineVersion`	Yes	The baseline used.
`brokenAtBaseline`	Yes	Findings that fail even at the baseline version — fix first, they are not migration items.
`cloudBlockerCount`	Yes	Statements valid at the baseline but not in ABAP Cloud.
`cleanCoreVocabulary`	Yes	SAP's real ATC vocabulary for released-API/Clean Core checks — see docs/atc-vocabulary.json (F04).
`releasedApiFindings`	Yes	Released-API observations from the bundled SAP Cloudification snapshot (deprecated-API usage, direct non-released table access with successor hints, and which edition/source answered each one). Informational — NOT counted in cloudBlockerCount or score.
`releasedApiSnapshotDate`	Yes	Date of the bundled released-API snapshot the releasedApiFindings reflect.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.12.4Oct 7, 2026

addedOutput schema / properties / categories / items / properties / rewrite

Added value: +{
+  "additionalProperties": false,
+  "description": "Curated canonical Cloud rewrite for this category, when one is bundled.",
+  "properties": {
+    "after": {
+      "description": "ABAP Cloud skeleton it is usually rewritten to.",
+      "type": "string"
+    },
+    "before": {
+      "description": "Classic ABAP skeleton the category typically looks like.",
+      "type": "string"
+    },
+    "notes": {
+      "description": "Caveats — the recipe is illustrative, not drop-in.",
+      "type": "string"
+    },
+    "pattern": {
+      "description": "Name of the canonical rewrite pattern.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "pattern",
+    "before",
+    "after",
+    "notes"
+  ],
+  "type": "object"
+}

Changed7 schema fields changedv0.12.0Sep 12, 2026

addedInput schema / properties / edition

Added value: +{
+  "default": "s4hc",
+  "description": "SAP edition of the bundled Cloudification snapshot to check against: \"s4hc\" (default, SAP Cloud ERP Public Edition), \"btp\" (SAP BTP ABAP environment), or \"pce\" (SAP Cloud ERP Private Edition / on-premise). Release state and successors can differ by edition — the same object may be released in one and not yet in another.",
+  "enum": [
+    "s4hc",
+    "btp",
+    "pce"
+  ],
+  "type": "string"
+}

addedOutput schema / properties / cleanCoreVocabulary

Added value: +{
+  "additionalProperties": false,
+  "description": "SAP's real ATC vocabulary for released-API/Clean Core checks — see docs/atc-vocabulary.json (F04).",
+  "properties": {
+    "checks": {
+      "description": "The real ATC checks behind released-API governance (name, edition, note).",
+      "items": {},
+      "type": "array"
+    },
+    "variants": {
+      "description": "The real ATC check variants, current and deprecated-with-successor.",
+      "items": {},
+      "type": "array"
+    }
+  },
+  "required": [
+    "checks",
+    "variants"
+  ],
+  "type": "object"
+}

addedOutput schema / properties / edition

Added value: +{
+  "description": "SAP edition the released-API findings were checked against.",
+  "enum": [
+    "s4hc",
+    "btp",
+    "pce"
+  ],
+  "type": "string"
+}

changedOutput schema / properties / grade / description

Previous value: -"Clean Core tech-debt grade banded on blocker density: A = no blockers, B = ≤ 0.5 blockers/file, C = ≤ 2 blockers/file, D = more. The same objective count as the score, sized for assessment reports."New value: +"Blocker-density tech-debt grade (see gradeMeaning): A = no blockers, B = ≤ 0.5 blockers/file, C = ≤ 2 blockers/file, D = more. The same objective count as the score, sized for assessment reports."

addedOutput schema / properties / gradeMeaning

Added value: +{
+  "const": "blocker-density",
+  "description": "What `grade` means: a banding of blockers per file. NOT SAP's own Clean Core Level A–D (see cleanCoreVocabulary.cleanCoreLevels for those) — do not conflate the two.",
+  "type": "string"
+}

changedOutput schema / properties / releasedApiFindings / description

Previous value: -"Released-API observations from the bundled SAP Cloudification snapshot (deprecated-API usage, direct non-released table access with successor hints). Informational — NOT counted in cloudBlockerCount or score."New value: +"Released-API observations from the bundled SAP Cloudification snapshot (deprecated-API usage, direct non-released table access with successor hints, and which edition/source answered each one). Informational — NOT counted in cloudBlockerCount or score."

changedOutput schema / required

Previous value: -[
-  "verdict",
-  "score",
-  "grade",
-  "cloudBlockerCount",
-  "fileCount",
-  "categories",
-  "brokenAtBaseline",
-  "releasedApiFindings",
-  "releasedApiSnapshotDate",
-  "baselineVersion",
-  "scopeNote"
-]New value: +[
+  "verdict",
+  "score",
+  "grade",
+  "gradeMeaning",
+  "cloudBlockerCount",
+  "fileCount",
+  "categories",
+  "brokenAtBaseline",
+  "releasedApiFindings",
+  "releasedApiSnapshotDate",
+  "edition",
+  "baselineVersion",
+  "scopeNote",
+  "cleanCoreVocabulary"
+]

First observedv0.4.5Jul 7, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations (readOnly, idempotent, non-open-world) already establish the safety profile, and the description adds substantial context beyond them: static/parser-level scope, that released-API observations are snapshot-dated and kept separate from the blocker count, how the A–D grade is computed (blocker density, not SAP's Clean Core Level), and what a 'ready' verdict does and does not mean.

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

Conciseness4/5

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

Purpose and mechanism are front-loaded, and the caveats and example all earn their place given the tool's complexity. The opening sentence is dense and em-dash-heavy, and some grade/verdict caveats could be tightened, but there is little pure filler.

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

Completeness5/5

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

An output schema exists, yet the description still pre-empts the key interpretive questions: what categories of findings appear, what the score and A–D grade mean, and why they are not SAP's Clean Core levels. Nothing an agent needs to select or call the tool correctly is missing.

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 the baseline is 3; the description adds real value by explaining why baselineVersion exists (it separates broken-anyway code from true cloud blockers) and that the edition snapshot's release state can differ per edition, going slightly beyond the schema text.

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 (Assess) and resource (ABAP source → Cloud readiness) and explains the exact mechanism: parsing twice at a classic baseline and at Cloud, then diffing to separate genuine blockers from pre-existing broken code. It clearly distinguishes itself from siblings such as check_released_api and lint_abap by naming what it does and does not cover.

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

Usage Guidelines5/5

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

Explicit triggers are given ('is this code cloud-ready / Clean Core compliant / S/4HANA-cloud safe', before porting classic ABAP, graded tech-debt of an abapGit export), plus explicit exclusions: not exhaustive dependency discovery, no SAP connection, no ATC execution, and a 'ready' verdict is not certification. It also routes to the authoritative alternative (ATC check with named variants).

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

Deploy Server