Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@ecom-mcp why is order ord_pick_002 stuck?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP server that lets an AI agent investigate stuck orders, surface fulfillment anomalies, and create escalation records — turning a multi-tab ops investigation into a single natural-language query.
Deployed on Railway with a PostgreSQL database. Connect any MCP-compatible client to the hosted URL and start querying immediately — no local setup required to evaluate.
https://ecom-mcp-production-f5bf.up.railway.app/sseThe server and its PostgreSQL database are both running on Railway. The /sse endpoint is live and accepting MCP client connections.
git clone https://github.com/beinghadibadami/ecom-mcp.git
cd ecom-mcp
npm install
cp .env.example .env
# add GROQ_API_KEY and MCP_SERVER_URL=https://ecom-mcp-production-f5bf.up.railway.app
npm run client:remote -- "why is order ord_pick_002 stuck?"The client prints each tool call and result as it runs, then a [final answer].
Related MCP server: ShopBot AI MCP Server
Tool | Access | Description |
| Read | Full order details and line items for a given order ID |
| Read | Payment state (captured / failed / refunded / pending) and amount |
| Read | Current stage, hours in stage, carrier, tracking, and error reason |
| Read | Orders breaching SLA thresholds with hours overdue and escalation status |
| Write | Creates or returns an existing escalation (idempotent). Blocked at the business layer if no confirmed anomaly exists |
src/constants.ts)Stage | Threshold |
Picking | 8 hours |
Packing | 4 hours |
Carrier handoff | 48 hours |
Thresholds are enforced in code — the model never invents or infers them.
Order ID | Scenario |
| Fully delivered, no issues |
| Stuck in picking (~12 h, threshold: 8 h) |
| Stuck in packing (~7 h, threshold: 4 h) |
| Stuck at carrier handoff (~60 h, threshold: 48 h) |
| Failed payment, no fulfillment triggered |
| Stuck in picking, already has an existing escalation |
Ops Engineer (natural-language query)
↓
Groq client — llama-3.3-70b-versatile
drives multi-turn tool-call loop (max 10 iterations)
↓ MCP JSON-RPC over SSE
MCP Server (Railway) — SSEServerTransport
↓ pg connection pool
PostgreSQL (Railway) — orders, payments, fulfillments, escalationsTransport is selected by environment: MCP_TRANSPORT=http → SSE (Railway), otherwise stdio (local dev).
Escalation enforcement — 3 layers
A write operation that creates a manager-review ticket needs to be safe. Enforcement works at three independent levels:
System prompt — instructs the model to only call create_escalation on explicit single-order investigation requests, never during general listing queries
Business layer — hasConfirmedAnomaly() re-queries the database before any insert; if no SLA breach or payment failure is confirmed, the function returns a blocked error and nothing is written
Database constraint — UNIQUE on escalations.order_id prevents duplicates even under concurrent requests
Listing vs. investigation intent
General listing queries ("show me flagged orders") call list_flagged_orders and return evidence only. Specific order queries ("investigate ord_pick_002") follow the full chain and may escalate. This distinction is enforced in the system prompt and backed by the business layer — listing can never accidentally trigger a write.
Idempotency
create_escalation called twice for the same order returns created: false with the existing record. The anomaly gate still runs on the second call, so only genuinely anomalous orders can ever hold an escalation.
Tests use Node's built-in test runner against a live local database — no mocking.
# make sure local DB is running and seeded first
npm testTest | What it checks |
Allowed path |
|
Blocked path |
|
Idempotency |
|
Payment failure |
|
Frontend, authentication, real payment provider integrations, and CI/CD are intentionally excluded per the assignment brief.
This server cannot be deployed
MCP server for building and testing AI agents with multi-model experimentation and insights.
Hosted MCP for e-commerce: live product catalog, stock, and pricing for AI agents.
One MCP server that gives your AI agent search, AI answer, social, ad and lead data.
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
