Everything in the atlas

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.

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.

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.

The repository the package declares has been deleted — verified against the GitHub API, not just a failed fetch. The package is still on npm, so it installs; the source it was published from is no longer readable, which is a harder thing to discover than a stale version number.

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

No public repository is declared on the package, so the README is the documentation.

No published releases; repository quiet for 28 months.

Server side only, and deliberately: the author states there is no realistic way to support the SSE streaming a client needs, so there are no notifications, no `listChanged`, no `subscribe` and no logging. It is also frozen — protocol versions up to 2025-11-25 and no further, with everything after that in a separate V2 SDK, so starting here today is starting on a closed branch.

Stateless by design: with no `Mcp-Session-Id` and no SSE, notifications of any kind, `resources/subscribe` and stream-close cancellation are excluded, which the author states are protocol-level impossibilities on stateless ICF rather than gaps to be filled later within this design. ABAP Cloud is not supported and not planned, the stated reason being SAP pushing its own MCP strategy and features in BTP; the first iteration targets 7.5x classic, with 7.02 to 7.4x served from a separate generated downport repository. No authorization object and no default auth check are delivered, so a user who may call the ICF node may call every `AREA`/`SERVER` registered under it until `check_authorization` is redefined.

Not a substitute for testing in a system: the README states that any class calling the database, classic BAPIs or HTTP is shimmed out and stays an on-stack ATC and ABAP Unit concern, and that an off-stack green is CI-grade provenance rather than an in-system pass. It also assumes a particular shape of project. The ABAP has to be abapGit-serialised into a Git repository, Node.js 22 or later has to be available locally and in CI, and the CI has to be GitHub Actions.

No published releases; repository quiet for 34 months.

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

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.

Configuration over an API you must already have entitled and provisioned; and the smallest of these repositories, so what it covers is what its config file happens to name.

Not reachable Not reachable since 2026-10-20.

Functional boundary `run_class` executes code in your system — that is the point and it is also the risk.

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.

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.

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.

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.

It lives inside Eclipse and inherits everything that implies — the session is a developer's, not a pipeline's. And it is version-bound: ADT 3.60 or newer for 0.5.1, with 0.3.x the path for ADT 3.58 and 3.59.

It administers a live Cloud Foundry landscape: `Apps`, `Organizations`, `Spaces`, `ServiceInstances` and `SecurityGroups` all carry create, update and delete alongside list and get. What a caller can reach is set by the role they hold, and the three templates in `xs-security.json` are MCPViewer for read, MCPEditor for read and write, and MCPAdmin for full administrative access.

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.

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

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.

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.

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.

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.

Not where the records sit anywhere but [SAP HANA Cloud](artifact:btp-hana-cloud): the similarity search and the single retrieval method are both written against its vector engine, and the embeddings and the chat call go through [SAP AI Core](artifact:btp-ai-core), so a project without both has nothing here to call. Not where the dependency has to be an SAP-supported one either: the README states that the plugin is not an official SAP product and is published as a community contribution.

Not published to npm. Install from source.

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.

Built and last touched in the same week of March 2026, so the maintenance reading is what it is — the authentication work is the reason to look, and a stalled repository is the reason to read it before depending on it.

A thin declaration over CPI's APIs: it reaches what those APIs expose and nothing else, and it inherits whatever the tenant's own authorisations allow.

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.

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.

In the Eclipse mode the server lives in a developer's IDE, binds to 127.0.0.1 and answers any request carrying an `Origin` header with HTTP 403, so a pipeline or a remote agent has nothing to reach; the standalone mode on the runtime of the ADT for VS Code extension is the documented route with no IDE open. A new connection starts in write mode, so the 11 write tools are live against a connected system until someone presses Toggle Read-Only. The dropins route for the two bundles is documented as untested.

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.

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

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.

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.

Its maker offers it commercially.

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.

The declared repository is archived.

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.

Not reachable Not reachable since 2026-10-20.

Functional boundary What it exposes is whatever somebody put in the configuration table, which moves the governance question inside the SAP system and out of the server — an advantage if that table is controlled and a hazard if it is not. The web management interface is a second surface to secure alongside the MCP one.

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.

Business Source License 1.1, which is source-available rather than open source: reading and evaluating are fine, and production use is restricted until the licence's change date. That is a procurement question, not a technical one, and it is the thing to settle first. Read-only also means read-only — no modelling, no loads.

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.

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.

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.

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.

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.

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

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.

It says so itself, in bold, and the atlas repeats it: not legal advice and not a compliance decision. Only SAP, your contract, or SAP support can answer bindingly, and the skill routes legal, commercial and roadmap questions there rather than guessing at them. Treat the output as evidence gathered, not as a verdict.

It reaches a data warehouse, so what an agent can see is business data by definition — the SQL sanitisation and PII filtering in the server are there because of that, not instead of a decision about it. And the guidance is Datasphere-shaped: nothing here transfers to a HANA Cloud database used directly.

Host-specific: outside Kiro the automatic context activation is the part that does not come with it, and what remains is prose you would have to wire in yourself. Breadth over depth by design — thirty-five skills across six product areas is an orientation layer, not a substitute for the focused sets in each.

Ninety tools is a large surface to put in front of a model at once, and client-credentials OAuth means the tenant sees one identity rather than the person asking. Content transport and user management sit in the same tool list as reading a story.

The maintainer states it is unofficial, not endorsed by SAP, and that it uses authenticated Hub web and catalogue endpoints and browser session cookies in ways SAP's terms of service, SAP account terms or an organisation's own policies may restrict. The same README asks the reader not to use it for production, broad distribution or shared access without explicit approval, and says that installing it grants no permission to automate SAP services.

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.

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.

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.

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.

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.

What it returns is planning material, not a commitment, and the monorepo labels the server's role "future/planned features (planning only)". The maintainer also states it is unofficial, not endorsed by SAP, and that it uses authenticated Road Map Explorer web endpoints and browser session cookies in ways SAP's terms of service or an organisation's policies may restrict, with production, broad distribution and shared access called out as needing explicit approval. An account that requires MFA has to be bootstrapped once through a visible browser.

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

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.

Its maker offers it commercially.

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.

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.

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.

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

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

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