Everything in BTP/BAIP

It stops at the `AuthInfo` and the raw bearer token, and the README lists what stays with the consuming server: rate limiting, the scope and tool policy, the MCP transport, the SAP HTTP client's headers, and helmet-style hardening. The one piece of hardening it constrains rather than defers is the cross-origin opener policy, which it deliberately leaves unset because popup-based OAuth breaks under it. It is ESM-only on Node 22 or later and shares the host's Express and MCP SDK instances as peer dependencies, so a server on Express 4 cannot take it.

The maintainer states it is unofficial, not endorsed by SAP, and that it automates authenticated SAP web endpoints and browser session cookies in ways SAP's terms of service or an organisation's own policies may restrict. Password login is confined to `accounts.sap.com` and the standard SAP Cloud Identity Services tenant domains: a custom IAS domain, or a login that conditional authentication delegates to a corporate identity provider, fails closed before the password is filled and has to be completed through an interactive login instead.

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 library a VS Code extension calls, not something installed and run on its own; there is no documented standalone CLI. No public repository either, so what it does is read from its own README rather than checked against source.

It expects a real landscape, not just a project: a `.service.metadata` file naming the Mobile Services app, endpoint and destination, the Cloud Foundry CLI, and access to a BTP Cloud Foundry environment. From 0.4.0 macOS support is ARM64 only — Intel Macs are not supported — alongside Linux and Windows on x64 and ARM64.

Specific to MDK metadata projects — nothing here builds or deploys a CAP service or a plain Fiori app. Closed-source, under SAP's own developer licence rather than a public repository.

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.

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.

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.

Quiet No published releases; repository quiet for 54 months.

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

The exported file list is hard-coded, so a dev space whose setup lives in files the readme does not name is not carried across; the roadmap lists making the list flexible as open work. Nothing from the BAS profile is in the zip, so a developer who wants the colour scheme, the keymaps or the installed extensions uses the BAS profile export on its own.

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.

The declared repository is archived.

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.

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.

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

It is a catalogue of SAP's objects and not a reading of your code: it states that an object is not released, never that you used it, and the finding is the ATC check's. For SAP Cloud ERP Private the files exist for feature pack stack releases only, with no update per support package, so a system between two stacks is checked against its stack's file.

Design-time only: no message monitoring, no deployment, no runtime status. That is a different server in this same section, and the two do not overlap.

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.

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.

Its own feature comparison marks connection pooling, automatic reconnect, active-active reads, client-side data encryption, statement distribution, Kerberos authentication, the hdbuserstore, promises and TypeScript types as [@sap/hana-client](https://www.npmjs.com/package/@sap/hana-client) only, so a service that wants a pool or a promise API writes both itself over a callback interface. OpenSSL is its one security provider where the other driver lists SAP CommonCryptoLib, OpenSSL and MSCrypto, and it runs on Node.js 18 or later.

It acts on a real account. Authorisation is the caller's own — single sign-on through the SAP Default Identity Provider, across the global accounts that identity reaches — so what it can change is what you can change, and an agent invoking it is doing administration rather than proposing it. No public source, so what it exposes is what the documentation says it exposes.

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

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

It deploys and undeploys, and it enumerates credentials, keystores and OAuth2 configurations. Listing security material is a read, and it is still a read of the thing that protects everything else the tenant talks to.

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.

It reads the landscape inventory, not the systems in it — nothing here reaches a running application, and nothing here changes anything. A landscape description is also commercially sensitive in its own right: versions and hosts are what a targeting exercise starts from.

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.

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.

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.

A tenant with its own model layer, its own transport and its own user administration — content moves between tenants through export and import jobs rather than through your pipeline, and planning brings a calendar and a workflow that a reporting-only use never touches.

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.

SAP's own guidance is narrower than the service's reach: it names standalone, single-tenant applications that do not connect to other applications as the fit, and says to stay on [the HTML5 Application Repository](artifact:btp-html5-application-repository) and the application router where those meet your needs better. Four hard limits decide it before taste does — 300 requests per second per subaccount, ten retained versions per application, 100 MB per application and 400 MB for the deployment archive.

1 of 8 plans deprecated.

It presumes the estate it governs: intelligent content is installed and viewed rather than authored, and the catalog is only as useful as what has been published into it. The Databricks path is a direction data goes, which is a decision about where analytics happens and not only about a tool.

A tenant with spaces and a role model, not a database you point an application at — privileges are granted per space, and what somebody can model depends on the scoped role they hold. Federation is the default answer to moving data, and where it is not, a load has to be scheduled and watched.

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.