commerce-mcp
An MCP control plane for SAP Commerce Cloud that exposes safe, read-only tools to LLM agents for inspecting types, running FlexibleSearch, and validating ImpEx.
README
commerce-mcp
An AI / MCP control plane for SAP Commerce Cloud (Hybris).
๐ Live site: https://alextsvetkov.github.io/commerce-mcp/
commerce-mcp exposes a SAP Commerce estate to LLM agents and developer copilots as a set of safe, typed, read-only tools over the Model Context Protocol (MCP). Instead of clicking through HAC and Backoffice, an engineer (or an agent acting on their behalf) can ask:
"Describe the
Ordertype." "Why did orderPROD-4471fail validation?" "Write ImpEx to add aloyaltyTierattribute toCustomerโ and validate it against the live model first."
โ ๏ธ Status: early scaffold. The tool surface, safety model and mock connector are real and tested; the live Hybris connector is a documented extension point, not yet implemented. See Roadmap.
Why this exists
SAP Commerce is powerful but opaque and expertise-gated. Every meaningful interaction โ inspecting the type system, running a FlexibleSearch, writing correct ImpEx, tracing an order โ requires deep tribal knowledge and manual navigation. LLMs can't help today because they have no safe, structured way in.
commerce-mcp is that way in. It is the "hands and eyes" that make a legacy commerce platform legible to agents โ collapsing the single biggest cost driver on any SAP Commerce program: scarce expertise and slow onboarding.
See docs/ (the GitHub Pages site) for the full benefits narrative.
Design principles
- Read-only by default. Every shipped tool is non-mutating.
run_flexible_searchrejects anything that isn't aSELECT; write paths (applying ImpEx) are deliberately out of scope for this surface and require separate, explicit authorization. - Safe by construction. Row caps, keyword denylists, and (planned) PII redaction + audit logging are product features, not afterthoughts.
- Offline-first. A fixture-backed
MockConnectormakes the entire tool surface runnable and testable with zero configuration โ no live instance needed for demos or CI. - Transport-neutral core. Tools are plain (schema, description, handler) triples; MCP is one adapter. A CLI or HTTP surface can reuse the same catalogue.
Architecture
LLM / Agent (Claude, Copilot, โฆ)
โ MCP (stdio)
โโโโโโโโโโโโโผโโโโโโโโโโโโ
โ commerce-mcp server โ src/server/index.ts
โโโโโโโโโโโโโโโโโโโโโโโโโโค
โ tool catalogue โ src/tools/index.ts (zod-typed, read-only)
โโโโโโโโโโโโโโโโโโโโโโโโโโค
โ CommerceConnector โ src/types.ts (interface)
โ โโ MockConnector โ fixtures โ offline
โ โโ LiveConnector* โ HAC / OCC / read-only DB view (*planned)
โโโโโโโโโโโโโโโโโโโโโโโโโโ
โ
SAP Commerce Cloud (Hybris)
Tools (v0.1)
| Tool | Purpose |
|---|---|
describe_type |
Full definition of an item type (attributes, parent, deployment table). |
list_types |
Enumerate type codes, optional substring filter. |
run_flexible_search |
Execute a read-only FlexibleSearch SELECT, capped rows. |
validate_impex |
Statically validate ImpEx against the live type model before applying. |
Quick start
npm install
npm run build
npm start # runs the MCP server on stdio against the MockConnector
npm test # unit tests, no live instance required
Use from an MCP client
Add to your client's MCP server config (example for a Claude-style client):
{
"mcpServers": {
"commerce": { "command": "node", "args": ["dist/server/index.js"] }
}
}
Roadmap
- [ ]
LiveConnectorover HAC + OCC + a read-only DB view. - [ ] PII redaction layer + structured audit log for every tool call.
- [ ]
explain_business_process,list_feature_toggles,trace_ordertools. - [ ]
zod-to-json-schemawiring so tool input schemas are fully published to the client. - [ ] Opt-in, separately-authorized write surface (apply validated ImpEx).
Contributing
See CONTRIBUTING.md. This project follows conventional commits and keeps generated code out of version control.
License
MIT ยฉ 2026 Aliaksandr Tsviatkou
Honest assessment
From the v2 self-critical analysis. Scores use Gap ยท Value ยท Moat ยท Time-to-revenue ยท Risk (for Risk, higher = safer). Prior art is named deliberately โ "no competitor" is almost never true.
Scores: Gap 5 ยท Value 4 ยท Moat 3 ยท TTR 4 ยท Risk 3 (higher=safer)
- Prior art / competition. MCP is new; SAP's Joule/CX AI is storefront-facing, not developer/ops-facing. Thin prior art โ the strongest of the suite.
- True differentiator. Depth and safety of type-system / ImpEx / FlexibleSearch semantics, and being the first safe agent entry point others build on.
- Kill criterion. If target teams won't let an agent touch prod data even read-only, and won't pay for a sandboxed variant, the wedge is weaker than it looks.
- Verdict. Build this as the one commercial wedge โ but from public HAC/OCC APIs, never internal employer code.
See the full landscape, go-to-market and the IP / conflict-of-interest discussion in sap-commerce-general-ideas-for-startup.md.
Part of a suite of backend tools for SAP Commerce Cloud. commerce-mcp is the AI-native flagship; sibling projects cover schema migration, ImpEx tooling, tracing, upgrades, and eventing correctness.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.