The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Bw Modeling MCP
MCP server for agentic AI-assisted development in SAP BW/4HANA
Install
npm install -g bw-modeling-mcpInstall command taken from the project's README or registry entry. Always review code before running it.
README excerpt
Read full README on GitHub →bw-modeling-mcp
A Model Context Protocol (MCP) server that enables AI assistants like Claude to work directly inside SAP BW/4HANA or SAP BW 7.5 on HANA systems — reading, creating and modifying BW modeling objects via the same internal SAP APIs that Eclipse BWMT and the BW/4HANA Cockpit use: the BW Modeling REST API (/sap/bw/modeling/) for objects, queries and live data, the ADT API (/sap/bc/adt/) for the ABAP and AMDP routines BW generates, the BW/4HANA manage API for the request monitor and runtime, and the Push API (/sap/bw4/) for data loads.
This is not a simulation. Every tool call connects to a live BW system — write operations produce real changes.
☁️ Running on SAP BTP Cloud Foundry
Besides stdio, the server can run as an HTTP service on SAP BTP Cloud Foundry with XSUAA
OAuth in front and a BTP destination behind — either a shared technical user
(BasicAuthentication) or principal propagation, where each caller reaches BW as
themselves and BW applies their own authorizations.
Three role collections decide what a user is offered: BW MCP Reader (everything that only reads), BW MCP Analyst (a small reporting client — run queries and understand what they return) and BW MCP Developer (everything, including changes).
stdio is unchanged — npm start behaves exactly as before. Setup:
docs/CENTRAL-HOSTING-SETUP.md (step-by-step) and
docs/CLOUD-FOUNDRY.md (reference).
What central hosting changes
| Scenario | stdio only | Hosted on BTP |
|---|---|---|
| One analyst, one BW system | runs on the analyst's machine | server-side, the analyst logs in with their own identity |
| Several analysts, one server | not possible, no central auth | all log in via BTP, each caller's identity reaches BW |
| Tool permissions | none — whoever runs it can call every tool | granted per role, independent of BW authorizations: a BW developer can be read-only in the MCP, or the querying tools can be withheld from someone who may otherwise view data |
| BW authorizations | enforced through the user's own credentials | unchanged, still fully enforced — with principal propagation each caller acts as themselves, never as a shared identity |
| Audit trail | limited | XSUAA logs every login; with principal propagation the BW session log shows the real user |
A new tool stays unavailable to read-only callers until it is explicitly classified as a
read, so the surface never widens by accident; write implies read, never the reverse.
The three role collections are a starting point and can be split further in xs-security.json.
Principal propagation additionally needs a certificate rule and ICM trust on the BW side.
System Compatibility
Similar plugs
Reverse engineer anything with agents, from app behavior down to native binaries.
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype…
A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io