Everything in the atlas

Every gate here runs off-system, so what the class does on a real system and what the view does on the oldest UI5 release it has to serve are what the `pitfalls` catalogues carry and no local run can see. It runs abap2UI5 app classes, so ABAP that is not one has nothing here to deploy into. In system mode the sandbox tools are not offered, and an `app_act` event runs on the system as the configured user.

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.

Written for Amazon Q Developer and Kiro, and the central deployment path is ECS Fargate — the further you are from AWS, the more of it is scaffolding you do not need. Python rather than the Node most of this group uses. Its README says the repository is no longer maintained and that the latest version of ABAP Accelerator is shared after registering with AWS for [Modernization Agents for SAP on AWS](https://github.com/aws-for-sap/Modernization-Agents-for-SAP-on-AWS).

A Python 3.10+ CLI, installed with pipx rather than through any SAP-provided package manager. Its own README lists what it does not do yet: where-used, syntax check and unit test runs — for those it says to reach for [ADT/Eclipse](external:eclipse) or an MCP server. First release, v0.1.0, and no standalone LICENSE file in the repository — the MIT grant is in the README and in pyproject.toml's project metadata rather than its own file.

Commercial Its maker offers it commercially.

Functional boundary The MIT licence covers the connector only: connecting to SAP needs a licensed ABAPilot backend installed in your system, so this is a commercial decision wearing an open-source badge on one half. Its own published checks did not cover writes, activation, transports or authorisation boundaries.

A system that reports itself productive, or whose role the probe cannot prove non-productive, is write-locked with no override, so changing code in production is not something this does. The permission ladder constrains the package, object name and transport request the server itself passes on a write, and is not a sandbox around ABAP it executes: `abap_run`, `abap_test` and the opt-in `core.eval` run under the connected technical user's SAP authorisations, which is where the boundary actually sits. Data preview, dump variable contents and driving a transaction by batch input stay off in every mode, `admin` included, until each is named explicitly.

Classic BOPF only: business objects of the ABAP Programming Model for SAP Fiori are not handled, and on [the BTP ABAP environment](artifact:btp-abap-environment) or S/4HANA Public Cloud classic BOPF enhancements do not exist. It is version 0.1.0, verified on S/4HANA 2025 (SAP_BASIS 816) on-premise only, and [arc-1](artifact:arc-mcp-arc-1) still marks the plugin API it is built on as experimental. ARC-1 loads no extensions on its multi-target routes and offers none of these tools in its `hyperfocused` tool mode.

The diff holds only while the object is inactive, since after activation the previous version is gone and a watched journal directory is what the maintainer points to instead. It adds no write path of its own: the IDE writes through SAP's extension, and the README states arc-1 can stay on `SAP_ALLOW_WRITES=false`. DDIC metadata files are skipped, because SAP's own stub for them says they are not supported in ABAP development tools for VS Code.

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 S/4HANA Public Cloud or [the BTP ABAP environment](artifact:btp-abap-environment), where the README states there is no `SUBMIT`, NAST or SOAP-RFC; the floor elsewhere is SAP_BASIS 7.50, the `/sap/bc/soap/rfc` service active, and an SAP user with `S_RFC` on the kit's function group as well as the authorizations for the reports and the spool. Print output is NAST messages only, so S/4 Output Management through BRF+ or APOC is outside it, and editing covers SmartForms alone, with Adobe Forms and SAPscript previewable but not editable. A report that opens a popup, calls a screen or is a dialog transaction cannot be run at all.

Freestyle SQL and `abap_run` mean an agent can read data and execute code, which is well past reading source. Neither is something to grant on a system where the distinction between development tooling and business data matters.

A compiled binary rather than an npm package, shipped prebuilt per platform and through pip and uvx. It collects anonymous usage telemetry by default, switched off with `--no-telemetry` or `DATAZOO_DISABLE_TELEMETRY=1`. And the BW reach is what distinguishes it — if the work is plain ABAP, that half is weight you are not using.

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.

Development and sandbox systems only: the README warns against pointing it at production. Transport release is never executed, since the tool exists to show the policy stopping it, and separation of duties is checked against the `identity.approvers` list in the policy file rather than against SAP authorisations, so it holds as far as that file does and no further. The write path has been tested with ABAP classes and other object types may need adjustments, there is deliberately no tool that creates or deletes an object, and one server instance serves one SAP system.

Its own README opens by calling the server experimental. It also writes: locking, editing and activating in a system an agent can reach is a permissions decision before it is a tooling one.

Every tool its README lists reads — Get and Search, nothing that writes. Locking, editing, activation and transports are the other server, [mcp-abap-abap-adt-api](artifact:mario-andreschak-mcp-abap-adt-api), and mixing the two is how you end up with two MCP servers pointed at one system.

There is nothing to clone here: "Access is provided through a registration page. Once registered, you will receive access to the GitHub repository containing the agents, deployment guides, and documentation", and that repository answers 404 to anyone who has not registered, so neither the agent code nor the deployment guides can be read before the form is filled in. AWS states the agents are published as an unsupported solution, with customers responsible for testing and securing the code before deploying in production, and that they are intended for non-production SAP environments rather than production systems. The documentation link in the README is still a placeholder.

Real SAP calls need the proprietary [SAP NetWeaver RFC SDK](external:sap-nw-rfc-sdk) and the `pyrfc==3.3.1` release the README calls archived and yanked, on Python 3.11, so without those only the demo backend answers. Not over HTTP as it stands: credentials are read from the environment for stdio, and the README says not to expose the server over HTTP without implementing the MCP authorization specification and deployment-level rate limiting. Multi-tenant auth and RBAC beyond the one server-wide policy, rate limiting, metrics and tracing, and deployment packaging are listed as not built. The result limits protect the client and not the system, since the README states they cannot reduce work already performed inside SAP, and the MCP tool annotations that describe read and write risk are advisory metadata rather than an authorisation boundary, so the service account's `S_RFC` and table authorisations are still what decides.

Reach is the reason to use it and the reason to be careful: reading cluster tables and spool output goes well past what a development tool is normally pointed at. Decide what an agent may reach before granting it, not after.

Read-only in practice, and the documentation is Korean; the tool names are English but the guidance around them is not.

Smart Form content cannot be read or written, and HR Forms (`PE51`) are not implemented. Installing it needs SAP GUI or WebGUI once, to register the OData services in `/IWFND/MAINT_SERVICE` and to redefine the write service in `SEGW`, and the extension is built against a locally linked ARC-1.

No license Neither the package manifest nor the repository tree declares a licence.

Functional boundary It consumes the `@experimental` public API, which the README says may break in any release. The RFC tool dials as one shared technical user with its own credentials, so SAP's log records that user and not the person behind the agent.

Every gate here runs off-system, so what the class does on a real system and what the view does on the oldest UI5 release it has to serve are what the `pitfalls` catalogues carry and no local run can see. It runs abap2UI5 app classes, so ABAP that is not one has nothing here to deploy into. In system mode the sandbox tools are not offered, and an `app_act` event runs on the system as the configured user.

It writes and it administers — ETL extraction and database user management are not read operations, and the same connection that profiles a column can move data out of the tenant. Masking is only as good as the configuration naming the fields, so an unlisted sensitive column is an unmasked one.

The embedded preview needs a system that accepts basic auth: the documentation states that pure SSO or SAML without a basic-auth fallback is not supported, and points at `external` mode, which opens the app in the normal browser with the existing SAP session. On the web only the language half runs; the preview with its proxy, traffic log and screenshot, Ctrl+F3 activation, the render gate, the workspace-wide check and the MCP servers are desktop-only. The agent app tools send nothing until `abap2ui5.agent.enableAppTools` is switched on in User settings, because an event they fire runs as the configured user and changes data on the system for real.

A system that reports itself productive, or whose role the probe cannot prove non-productive, is write-locked with no override, so changing code in production is not something this does. The permission ladder constrains the package, object name and transport request the server itself passes on a write, and is not a sandbox around ABAP it executes: `abap_run`, `abap_test` and the opt-in `core.eval` run under the connected technical user's SAP authorisations, which is where the boundary actually sits. Data preview, dump variable contents and driving a transaction by batch input stay off in every mode, `admin` included, until each is named explicitly.

It administers a real account through Core Services, so what it can change is what the caller can change. And the UI half depends on hosts that render mcp-ui or MCP Apps resources; elsewhere those five tools return markup nobody displays.

This is the database, not an application in front of it, so what an agent can read is whatever the connection user can read — the guardrails bound the shape of a query, not the sensitivity of what it returns. Grant the connection the rights you would grant a person.

Not for production: the README states local and development instances only, and the server refuses a HAC URL whose host is not private unless `HAC_ALLOW_REMOTE=true` overrides that guard. Masking applies to `config_get` only, so `logs_tail` and `monitoring_info` output, thread dumps included, is unmasked and may carry sensitive data, and whatever a tool returns goes to the MCP client and its model. Certificate checks are disabled whenever `HAC_INSECURE_TLS=true` is set, which the README names as typical for local HAC.

It fronts APIs you already have; nothing here reads a system's source or model, and a config file is only as good as the entity sets somebody wrote into it. OData V2 is the query surface it names.

Real SAP calls need the proprietary [SAP NetWeaver RFC SDK](external:sap-nw-rfc-sdk) and the `pyrfc==3.3.1` release the README calls archived and yanked, on Python 3.11, so without those only the demo backend answers. Not over HTTP as it stands: credentials are read from the environment for stdio, and the README says not to expose the server over HTTP without implementing the MCP authorization specification and deployment-level rate limiting. Multi-tenant auth and RBAC beyond the one server-wide policy, rate limiting, metrics and tracing, and deployment packaging are listed as not built. The result limits protect the client and not the system, since the README states they cannot reduce work already performed inside SAP, and the MCP tool annotations that describe read and write risk are advisory metadata rather than an authorisation boundary, so the service account's `S_RFC` and table authorisations are still what decides.

Business Source License 1.1: source-available, with production use restricted until the change date — settle that before anything technical. And the governed execution path in v0.2 does act on data, which is a different grant from the discovery the v0.1 baseline offered.

On ECC the S/4HANA `API_*` services that the three convenience readers default to do not exist, so each one has to be pointed at a Z service of your own or replaced by the RFC tools. `read_table` inherits `RFC_READ_TABLE`'s 512-byte row, so a wide table needs an explicit field list and some fields cannot be selected at all, and the bridge starts a Node process and a fresh logon per call, with no pooling. The audit log is one line per call that includes the call arguments, so every filter and WHERE clause sent to SAP is written to a file that then has to be handled as sensitive.

Read-only does not mean low-stakes: a complete picture of who can do what in an SAP system is exactly what an attacker would want, and the ready-made endpoint is the vendor's rather than yours — the README also documents running the server yourself. The authentication is careful; the question of what leaves your landscape is still yours.

If your tool reads the open skill standard directly, install [capire/skills](artifact:capire-skills) and skip the wrapper.

The embedded preview needs a system that accepts basic auth: the documentation states that pure SSO or SAML without a basic-auth fallback is not supported, and points at `external` mode, which opens the app in the normal browser with the existing SAP session. On the web only the language half runs; the preview with its proxy, traffic log and screenshot, Ctrl+F3 activation, the render gate, the workspace-wide check and the MCP servers are desktop-only. The agent app tools send nothing until `abap2ui5.agent.enableAppTools` is switched on in User settings, because an event they fire runs as the configured user and changes data on the system for real.

Every skill that touches ABAP needs [arc-1](artifact:arc-mcp-arc-1) itself connected to a real system; nothing else is universal. `modernize-ui5-app` and `convert-ui5-to-fiori-elements` specifically need [the UI5 MCP server](artifact:ui5-mcp-server) for TypeScript conversion guidance and the linter, `convert-ui5-to-fiori-elements` also needs [the Fiori MCP server](artifact:sap-ux-fiori-mcp-server) for its LROP scaffold, and `modernize-ui5-app` needs a browser MCP (Claude in Chrome or Claude's own Preview) for its final render-verification step, since an HTTP 200 alone does not catch a blank page. A skill file alone, without the servers a given skill needs, has nothing to act on.

Any run nobody is watching: the drawing tools work only while the draw.io canvas at `http://localhost:3000/` is open and connected, so there is no diagram to produce on a build agent or a server. Nothing checks the result either, because the maintainer keeps a diagram linter on the [roadmap](https://github.com/etosin/arc-draw#-roadmap) rather than in the release. The maintainer marks the status early at v0.x, installs it from source, and records testing with Claude Code alone.

No license Neither the package manifest nor the repository tree declares a licence.

Functional boundary There is no licence, so there is no grant to use or redistribute it. Everything else is secondary to that. Note too that its 'verified' claim means the skill text was checked against itself by an evaluation suite — not that the advice was run against a CAP version.

Local scaffolding only. Its own Out of Scope list names deployment to Cloud Foundry or Kyma, XSUAA and IAS configuration or any other BTP service binding, the SaaS Registry and subscription flow to real tenants, and automatic migration from the legacy `@sap/cds-mtx`. For the concepts rather than the scaffolding step, the README points at the `multitenancy` skill in [skillOverflow](artifact:dankromp-skilloverflow) by [Daniel Krompaß](actor:dankromp), which covers the MTX sidecar, `xs-security.json`, tenant lifecycle hooks and the deployment path and runs no commands at all.

Knowledge with no reach: without an MCP server connected it can tell an agent what to write and cannot let it read or run anything. The rules target the ABAP Cloud development model, so a classic on-premise codebase is not what they are written against.

Not for S/4HANA Public Cloud or [the BTP ABAP environment](artifact:btp-abap-environment), where the README states there is no `SUBMIT`, NAST or SOAP-RFC; the floor elsewhere is SAP_BASIS 7.50, the `/sap/bc/soap/rfc` service active, and an SAP user with `S_RFC` on the kit's function group as well as the authorizations for the reports and the spool. Print output is NAST messages only, so S/4 Output Management through BRF+ or APOC is outside it, and editing covers SmartForms alone, with Adobe Forms and SAPscript previewable but not editable. A report that opens a popup, calls a screen or is a dialog transaction cannot be run at all.

The README tells you to fork before cloning, because Claude rewrites `references/` and `SKILL.md` in place as you use it, so a clone shared between people changes under all of them. Installing means `git` and `ln` on macOS or Linux and a symlink into `~/.claude/skills`. Fine positioning stays manual: the coordinates Claude writes can be rough apart from the centre coordinates of elements joined by a straight arrow and the containment relationships.

A requirement that needs code: the skill generates configuration and states that it says so instead of faking it. Dialog and container targets have no verified enter event, so a dashboard placed there loads only through its Refresh button. Production Processes are outside it — it wires PODs to them and does not design them.

The commands it writes stop production systems, delete data and import transports, which is why execution is deliberately somebody else's decision. BTP and cloud operations are explicitly out of scope and planned as a separate plugin.

It stops before the artifact: in the README's own words it does not generate or deploy complete iFlow artifacts, so building and shipping the integration flows themselves stays with a person and a tenant. Knowledge beside the work rather than a generator, and it reads nothing from a running tenant.

Not for a project below the 2211-jdk21.1 baseline: older releases and the JSP Accelerator are covered only as explicitly marked legacy material, so a JSP storefront or a pre-JDK-21 platform is outside what the guides are written against. Knowledge with reach only through one script — it can tell an agent what to write and, apart from `query-items.sh`, cannot let it read what a given system contains.

Three of its five reference corpora are not shipped: without an api.sap.com key and session cookie, a tenant bearer token and a local SAPUI5 fetch, the REST, MDO and UI5 tools return a message naming the preparation step that is missing. The HTTP transport has no authentication until `MCP_AUTH_TOKEN` is set, so anything past localhost needs that or an authenticating reverse proxy. Packing the ZIP, uploading it through Manage POD 2.0 Extensions and placing the widget in the POD Designer stay manual steps outside the agent, and the SAPUI5 fetch defaults to the SDK's newest version, which the README says is not the version a tenant runs. Node.js 22 or newer.

Its README calls it early-stage — the core workflows run end-to-end against real systems and packaging, documentation and polish are stated as still evolving. A Rust binary rather than an npm install, so the platform build matters.

GPL-3.0, which is a licence to read before vendoring any of it into something you ship. Forty plugins is also a lot of always-available surface — the ledger is there because breadth and verification pull in opposite directions, and it does not resolve that so much as report it.

It is a plugin for one server — its own — so it is a stack rather than a component. And the guard is only as good as the profile labels: a production system registered as `DEV` is a production system with the safety off.

Not a way to edit Office formats: the author states that access to a file does not automatically provide native editing of Word documents, spreadsheets or PDFs, and suggests starting with text-based content such as instructions, templates and reports. Not a control point either: a prompt telling the agent to ask for confirmation or to leave a template alone needs enforceable application controls where that is a business requirement, and the host application stays responsible for the authenticated request context and tenant isolation.

Not where the agent is reached over anything other than A2A: the README states the plugin does not speak anything other than A2A as @cap-js/agents serves it. Not where an upgrade has to be uneventful either — it pins @cap-js/agents to exactly 0.9.1, calls that package pre-1.0 and days old at the time of writing, and says this plugin inherits that instability and to expect breakage on upgrade.

Neither the package manifest nor the repository tree declares a licence.

Neither the package manifest nor the repository tree declares a licence.

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.

It is text processing, not an agent: there is no tool calling, no retrieval and no conversation. It needs SAP AI Core, and the backend half needs [@sap-ai-sdk/orchestration](artifact:sap-ai-sdk-orchestration) installed alongside it — an optional peer, so a frontend-only install stays lean.

Neither the package manifest nor the repository tree declares a licence.

Neither the package manifest nor the repository tree declares a licence.

An early alpha release whose README says to pin the version and test recipes against non-production data first. HANA synchronisation is snapshot-only and does not reconcile deleted rows, so a document for a row deleted in the source stays in the index. A recipe's field allow-list does not decide what the service account may read: the README states that field allow-listing does not replace SAP authorization, and that the package infers no SAP module semantics, authorization scope or safe fields from table names. Only Business Partner has a built-in recipe, every other dataset needs a `KnowledgeRecipe` written for it, and [Qdrant](external:qdrant) local mode is stated to be for development and smaller indexes.

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.

Development and sandbox systems only: the README warns against pointing it at production. Transport release is never executed, since the tool exists to show the policy stopping it, and separation of duties is checked against the `identity.approvers` list in the policy file rather than against SAP authorisations, so it holds as far as that file does and no further. The write path has been tested with ABAP classes and other object types may need adjustments, there is deliberately no tool that creates or deletes an object, and one server instance serves one SAP system.

Real SAP calls need the proprietary [SAP NetWeaver RFC SDK](external:sap-nw-rfc-sdk) and the `pyrfc==3.3.1` release the README calls archived and yanked, on Python 3.11, so without those only the demo backend answers. Not over HTTP as it stands: credentials are read from the environment for stdio, and the README says not to expose the server over HTTP without implementing the MCP authorization specification and deployment-level rate limiting. Multi-tenant auth and RBAC beyond the one server-wide policy, rate limiting, metrics and tracing, and deployment packaging are listed as not built. The result limits protect the client and not the system, since the README states they cannot reduce work already performed inside SAP, and the MCP tool annotations that describe read and write risk are advisory metadata rather than an authorisation boundary, so the service account's `S_RFC` and table authorisations are still what decides.

It is a plugin for one server — its own — so it is a stack rather than a component. And the guard is only as good as the profile labels: a production system registered as `DEV` is a production system with the safety off.

Any run nobody is watching: the drawing tools work only while the draw.io canvas at `http://localhost:3000/` is open and connected, so there is no diagram to produce on a build agent or a server. Nothing checks the result either, because the maintainer keeps a diagram linter on the [roadmap](https://github.com/etosin/arc-draw#-roadmap) rather than in the release. The maintainer marks the status early at v0.x, installs it from source, and records testing with Claude Code alone.

The README tells you to fork before cloning, because Claude rewrites `references/` and `SKILL.md` in place as you use it, so a clone shared between people changes under all of them. Installing means `git` and `ln` on macOS or Linux and a symlink into `~/.claude/skills`. Fine positioning stays manual: the coordinates Claude writes can be rough apart from the centre coordinates of elements joined by a straight arrow and the containment relationships.

Not on ABAP Cloud: the system tables and the classic Workbench APIs the screens use are not released for the ABAP Cloud language version, and there is no 7.02 version below the 7.50 floor either. Not where the full original function is needed, since only the listed transactions exist and about 300 buttons and fields are shown disabled. The authorization checks are rebuilt rather than the originals, which is why the README asks that the screens be tried with a restricted user on a sandbox before the ICF service is opened to more people.

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.