Shopify AI Ops Agent
🛍️ Shopify AI Operations Agent
Ein produktionsreifer autonomer E-Commerce-Operations-Agent, entwickelt mit LangGraph v1, Model Context Protocol (MCP 2026-07-28), FastAPI, PostgreSQL + pgvector, Redis, OpenTelemetry und strenger Human-in-the-Loop (HITL)-Risiko-Governance.
📖 Vollständige technische Dokumentation
Für detaillierte Architektur, Terminologien und Architectural Decision Records (ADRs) in ASD-STE100 (Simplified Technical English), siehe:
👉 DOCUMENTATION.md
Laden Sie das visuelle Präsentations-PDF herunter:
👉 architecture_diagram.pdf (oder unter http://localhost:8000/architecture.pdf)
🏗️ Zentrale Architektur-Invarianten
Pre-Execution Risk & Policy Gate: Destruktive Löschungen, finanzielle Budgets und ausgehende Kommunikationen lösen einen LangGraph-Interrupt (
interrupt_before) aus, der eine menschliche Genehmigung erfordert.Decoupled MCP Tool Layer: Alle Geschäftsfunktionen sind als 5 zustandslose MCP-Tool-Server (
Shopify,Analytics,Meta Ads,Communications,Trend Intelligence) gekapselt.Deterministic Business Analytics: Finanzkennzahlen werden mithilfe deterministischer SQL-Routinen berechnet, wodurch arithmetische LLM-Halluzinationen eliminiert werden.
Anti-Early-Victory Sensors: Der Agent fragt den Live-Zustand erneut ab, um mathematisch zu verifizieren, dass Mutationen stattgefunden haben, bevor er den Abschluss meldet.
Shift-Left Evals & Tracing: 28 automatisierte pytest-Testsuiten, ein Golden-Eval-Benchmark mit 17 Fällen und ein unabhängiges Critic-Agent-Audit (Score: 98.5/100, Grade: A+).
📁 Repository-Struktur
shopify-ai-ops-agent/
├── DOCUMENTATION.md # Full technical documentation (ASD-STE100)
├── architecture_diagram.pdf # 2-slide landscape architecture diagram
├── docker-compose.yml # Postgres (pgvector) + Redis + Jaeger + API
├── pyproject.toml # Dependencies & packaging
├── app/
│ ├── api/ # FastAPI routes (agent, approvals, health)
│ ├── agent/ # LangGraph state machine & specialized nodes
│ ├── mcp_servers/ # 5 Stateless MCP tool servers
│ ├── core/ # Security (HMAC-SHA256), Idempotency, Database
│ ├── rag/ # Hybrid Vector + BM25 search & brand guidelines
│ ├── static/ # Executive SaaS Cockpit UI & Command Palette
│ └── evals/ # Golden datasets & Critic Agent audit
└── tests/ # 28 automated unit, safety, and integration tests🚀 Schnellstart & Setup
1. Lokale Entwicklung
# Install dependencies
pip install -r requirements.txt
# Start the application server & dashboard
python -m uvicorn app.api.main:app --reload --port 8000Dashboard-UI:
http://localhost:8000/(Drücken SieCtrl + Kfür die Befehlspalette)Interaktive API-Dokumentation:
http://localhost:8000/docsArchitektur-PDF:
http://localhost:8000/architecture.pdf
🧪 Verifizierung & Evaluierungen
# Run full automated test suite (28 tests)
python -m pytest tests/ -v
# Run independent Critic Agent technical audit
python -m app.evals.judge_agentThis server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Get recommended by Amazon's AI. Hosted MCP server for Amazon listing compliance & generation.
Hosted Amazon Seller and Vendor MCP server for Claude, ChatGPT, Cursor, Codex, Gemini, Copilot.
Connect e-commerce and marketing data to AI assistants via MCP.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Thebeardedambivert/shopify-ai-ops-agent'
If you have feedback or need assistance with the MCP directory API, please join our Discord server