Everything in ABAP / ABAP Cloud

Stateful apps cannot be operated: a stateful session lives in one HTTP request and an MCP call is one request, so `app_start` refuses them. The repository carries no release yet and states the addon has not been run in production use, the 7.02 downport is lint-only with no 7.02 system having run it, and the ABAP Cloud HTTP service setup is written down but still to verify on your own system.

Its README says it plainly and so does this entry: this is not a simulation, every tool call reaches a live BW system, and write operations produce real changes. BW modelling objects are the definition of a warehouse — the blast radius of a wrong one is every report built on it.

Not for the replacement decision itself: the author states that a structural field mapping, a C1-release indicator or even an official-successor indication does not prove semantic or performance equivalence, and that the developer must validate business scope and authorizations for the intended use case. It is also not a complete catalogue, since 130,647 CDS entities entered the extraction queue and 121,303 were analysed successfully, and it carries one system's state: a later Feature Package Stack needs the analysis refreshed, because available CDS content and release status change.

Not an end-user app: it reads from any table the user names and writes into tables of the Z/Y namespace, with no authorisation check of its own, so the README asks a project to add its own checks on `S_TABU_DIS`/`S_TABU_NAM` and to restrict who may run it before it is used beyond a development system. XLSX upload and download are not ready for ABAP Cloud yet, and of the upload apps only the JSON one writes the file's rows back to the database.

Its README says it plainly and so does this entry: this is not a simulation, every tool call reaches a live BW system, and write operations produce real changes. BW modelling objects are the definition of a warehouse — the blast radius of a wrong one is every report built on it.

The app writes to whatever table is passed in the URL parameter `table` and carries no authorisation check of its own, so past a development system it needs authorisation checks added and a restriction on who may run it.

A descendant rather than a distinct idea: if what you need is the ADT surface itself, its ancestors are entered here too and one of them may already be in your stack.

A stopped program holds an SAP work process and its caller's request, so an interactive session is the wrong shape wherever that matters: one runs per SAP user at a time, other captures for that user are refused while it is open, and a Cloud Foundry deployment stays at one instance because the next call must reach the same process. Breakpoints in report and function-group includes are not accepted, and a message breakpoint catches `MESSAGE` statements only, so RAP messages from `new_message( … )` and BAPI return tables never stop a run. On SAP_BASIS 7.50 and older the system cannot name the session's debug user, so there `SAP_USER` is used behind Basic or cookie authentication only.

Single-tenant today, one technical user, with per-user principal propagation on the roadmap — so a shared deployment cannot yet act as the developer who asked. The sibling edition [ARC-1](artifact:arc-mcp-arc-1) speaks ADT directly if you would rather not depend on the language server.

Its README says it plainly and so does this entry: this is not a simulation, every tool call reaches a live BW system, and write operations produce real changes. BW modelling objects are the definition of a warehouse — the blast radius of a wrong one is every report built on it.

Two licences, by which package you install: the standalone server, `@mcp-abap-adt/core`, is AGPL-3.0-only, a licence to read before shipping anything built around it; the library, `@mcp-abap-adt/lib`, is Apache-2.0. The destination model also expects service keys sitting in a local directory, which is a secrets decision to make deliberately.

It puts create, update and delete on business entities behind natural language. Whatever the destination's principal may change, an agent may change — and "create a new customer" is a sentence, not a form somebody signed off.

OData v2 only, and untouched since August 2025 — the same author's [Go port](artifact:oisee-odata-mcp-go) is where v4 support and the tool-explosion work went.

Universal mode trades discoverability for size: one generic tool is harder for a model to pick correctly than a named one, which is why it is not the default. On a small service, standard mode is the better answer.

Stateful apps cannot be operated: a stateful session lives in one HTTP request and an MCP call is one request, so `app_start` refuses them. The repository carries no release yet and states the addon has not been run in production use, the 7.02 downport is lint-only with no 7.02 system having run it, and the ABAP Cloud HTTP service setup is written down but still to verify on your own system.

Archived The declared repository is archived.

Functional boundary With one SAP system the README says to point the client at that arc-1 directly. Version 1 exchanges tokens within a single subaccount, so backends spread across subaccounts are out; it keeps its session map in memory, so more than one instance needs sticky sessions or a shared store. It routes deterministically and runs no model, which is a different thing from an assistant that reasons across systems. The `/all` endpoint drops the per-connection isolation, and the maintainer's answer to that is a PROD backend set read-only at the SAP end rather than a tool surface that hides the writes.

Its README says it plainly and so does this entry: this is not a simulation, every tool call reaches a live BW system, and write operations produce real changes. BW modelling objects are the definition of a warehouse — the blast radius of a wrong one is every report built on it.

It answers about the object catalogue, not about your code: nothing here reads your system, so it will tell you a table is not released and not that you used it. That check is ATC's, and this is what makes ATC's answer actionable.

Not for the replacement decision itself: the author states that a structural field mapping, a C1-release indicator or even an official-successor indication does not prove semantic or performance equivalence, and that the developer must validate business scope and authorizations for the intended use case. It is also not a complete catalogue, since 130,647 CDS entities entered the extraction queue and 121,303 were analysed successfully, and it carries one system's state: a later Feature Package Stack needs the analysis refreshed, because available CDS content and release status change.

It sees [abap2UI5](artifact:abap2ui5-abap2ui5) only: the figures come from the framework's HTTP handler, its monitor hook and its draft table, so nothing outside abap2UI5 appears in them. The usage, error and performance tabs stay empty until the handler line is in place or the user exit sets `check_monitor_active`. Recording which employee used which application, when and how fast, is subject to works council co-determination in Germany (§ 87 (1) no. 6 BetrVG); user tracking is `HASH` by default, `NAME` stores user names, and the request recorder keeps the complete request and response of every roundtrip for two days by default.

Not as it stands on a system past development: it reads the contents of any table the user names without an authorisation check of its own, so access is bounded only by whatever restrictions exist on the underlying handler or service. The README asks for your own checks first, naming `AUTHORITY-CHECK` on `S_TABU_DIS`/`S_TABU_NAM`, and for a restriction on who may run the app. There is no 7.02 downport either, because the selection-screen dependency has no `702` branch.

It runs whatever SQL a user types without an authorisation check of its own, and the native path additionally uses ADBC, which bypasses ABAP authorisations and client separation; the README asks anyone running it beyond a development system to add authorisation checks and restrict who may start the app. The native console needs Standard ABAP, so on ABAP Cloud only the Open SQL console is available.

A stopped program holds an SAP work process and its caller's request, so an interactive session is the wrong shape wherever that matters: one runs per SAP user at a time, other captures for that user are refused while it is open, and a Cloud Foundry deployment stays at one instance because the next call must reach the same process. Breakpoints in report and function-group includes are not accepted, and a message breakpoint catches `MESSAGE` statements only, so RAP messages from `new_message( … )` and BAPI return tables never stop a run. On SAP_BASIS 7.50 and older the system cannot name the session's debug user, so there `SAP_USER` is used behind Basic or cookie authentication only.

Not in production: "This repository contains sample code which should not be used in production", and the README sends a production reader to the officially supported libraries instead.

LISA does the translation step only: it does not discover objects or manage transports, and its README pairs it with [an ADT MCP server](artifact:sap-adt-mcp-server) for those. Every write needs a transport request, and which object types it can write differs between public cloud or [the SAP BTP ABAP environment](artifact:btp-abap-environment) and on-premise or private cloud, and by release. Running it locally is meant for development and testing, not production.

It reads documentation, never a system: nothing in it opens a package.json, a CDS model or an ABAP client, so a question about what your own project does has to be answered elsewhere. The offline half is only as fresh as the submodules the last build pinned, and the index answers where something is written down rather than which of two packages fits a task.

It needs an S-user with SAP Support Portal access, so there is nothing to search without a support contract behind the login. The maintainer states it uses private SAP APIs behind authentication, asks the reader to check whether that use breaches SAP's terms of service, and disclaims both liability and any guarantee that it keeps working. MFA is handled only by typing the code into a visible browser, so a headless deployment cannot complete a login that demands one.

A sample that needs something the system provides is not here — the samples-stack repository holds the OData, RAP, WebSocket and launchpad demos, and samples-controls the rebuilds of the UI5 Demo Kit originals. Every class in `src/` keeps to controls and properties available since UI5 1.71 and not deprecated, apart from two clipboard samples marked `(UI5 1.119+)`, so a newer control is not demonstrated here. Numbers are handed out per repository and reused across the three, so `493` alone does not name a sample: `Z2UI5_CL_SMP_APP_493` is the Hello World here.

The 221 ports under `src/02` need a UI5 runtime newer than 1.71: they install and activate on any release, and on an older UI5 the newer control does not render. The `src/03` collection is hand-written for SAPUI5-only controls and needs a SAPUI5 bootstrap. There are no per-library branches, so pulling the whole repository is the one way in and the activation takes a few minutes.

Not the place to learn abap2UI5 itself: every package starts from a technology the system already provides, and the framework basics and the control gallery are the other two sample repositories, abap2UI5/samples and abap2UI5/samples-controls. Three packages are out of reach on ABAP Cloud, and `05` needs the 2021 release that carries RAP business events.