Skip to main content
Glama

ShopOps MCP

AI-powered server that implements the Model Context Protocol (MCP) for managing Shopify and WooCommerce stores.

License: MIT TypeScript MCP


Features

  • Store connectors for Shopify and WooCommerce.

  • 12 MCP tools covering inventory, pricing, customers, orders, product performance and reporting.

  • 4 MCP resources exposing store overview, inventory, recent orders and top customers.

  • Inventory forecasting using moving-average demand plus safety-stock calculation.

  • RFM-based customer segmentation (7 distinct segments).

  • Data-driven pricing analysis with margin-based optimization suggestions.

  • Order anomaly / fraud detection.

  • ABC analysis of product performance.

  • Automated daily and weekly reports.

  • Dual transport: local stdio and Streamable HTTP (MCPize).

  • TypeScript, @modelcontextprotocol/sdk v1.29+, Zod v4.

  • Free tier, plus a €29 lifetime Pro license.


Related MCP server: Ecommerce AI MCP

Quick Start

# 1. Install the package
npm i shopops-mcp

# 2. Create a .env file (see Configuration section)
cp .env.example .env

# 3. Run the server (local stdio mode)
npx shopops-mcp run --transport stdio

# 4. Or start the HTTP endpoint (MCPize deployment)
npx shopops-mcp run --transport http --port 8080

The server will read the environment variables, connect to the configured store(s), and expose the MCP tools and resources.


MCP Tools

Tool

Description

store_connect

Connects, lists, disconnects, or syncs a Shopify/WooCommerce store (action: "connect" | "list" | "disconnect" | "sync") and validates credentials.

store_demo_seed

Creates a realistic demo store (20 products, 40 customers, 150+ orders) so you can explore every tool without real store credentials.

inventory_status

Returns current stock levels, back-order flags and low-stock alerts.

inventory_forecast

Projects future inventory requirements using moving-average demand and safety-stock buffers.

pricing_analyze

Generates a price elasticity report and identifies under-/over-priced SKUs.

pricing_optimize

Suggests optimal price points based on margin analysis, sales velocity, and configurable pricing rules.

customers_segment

Performs RFM analysis and assigns customers to one of seven segments.

customers_churn

Scores customers for churn risk and provides retention recommendations.

order_anomalies

Detects potentially fraudulent or erroneous orders using pattern-recognition models.

product_performance

Conducts ABC analysis and returns contribution metrics per product class.

report_daily

Generates a JSON/CSV daily operations summary (sales, inventory, alerts).

report_weekly

Generates a weekly performance report with trend visualisations.


MCP Resources

Resource

Description

store://overview

High-level store metrics: product, order, and customer counts per connected store.

store://inventory

Low-stock alerts: active products with on-hand quantity ≤ 10, sorted lowest first.

store://orders/recent

The 20 most recent orders across all stores, with order number, total, status and date.

store://customers/top

Top 20 customers by total spending, with name, email and order count.


Configuration

ShopOps reads only a handful of environment variables. Store credentials are not env vars — they are passed to the store_connect tool at runtime (one connection per store), so the same server process can manage multiple Shopify/WooCommerce stores.

Variable

Required

Description

PORT

No

If set (or MCPIZE=true), the server runs as a Streamable HTTP endpoint on this port (default 8080) instead of local stdio.

MCPIZE

No

Set to true by the MCPize runtime to force HTTP transport.

LEMONSQUEEZY_LICENSE_KEY

No

Pro license key. Without it the server runs in Free tier (see Pro License).

A minimal .env is provided in .env.example.

Connecting a store

Shopify and WooCommerce credentials are supplied as parameters to store_connect, e.g.:

// Shopify
{ "action": "connect", "platform": "shopify",
  "store_domain": "myshop.myshopify.com", "access_token": "shpat_..." }

// WooCommerce
{ "action": "connect", "platform": "woocommerce",
  "store_url": "https://example.com", "consumer_key": "ck_...", "consumer_secret": "cs_..." }

store_connect returns a store_id that every other tool takes as input. To explore the server without real credentials, call store_demo_seed instead.

Roadmap (not yet implemented): report anonymization, S3 report export, and a configurable pricing-model / log-level are planned but not read by the current release.


Pro License

ShopOps ships in Free mode — store_demo_seed, store_connect, inventory_status, pricing_analyze, customers_segment, product_performance, and report_daily are open. The following tools require a Pro license:

  • inventory_forecast — moving-average demand forecasting + reorder points

  • pricing_optimize — actionable price-change recommendations

  • customers_churn — churn risk scoring + retention recommendations

  • order_anomalies — fraud / anomaly detection

  • report_weekly — week-over-week trend report + AI insights

Buy a Pro License (€29, lifetime, 3 machines): https://automatiabcn.lemonsqueezy.com/buy/cbbe44f0-a146-4c65-88c8-71f371037758

Or get the Indie MCP Stack Bundle (€69, all 4 servers).

export LEMONSQUEEZY_LICENSE_KEY=YOUR-KEY-HERE

Or in your MCP client config:

{
  "mcpServers": {
    "shopops-mcp": {
      "command": "npx",
      "args": ["-y", "shopops-mcp-server"],
      "env": { "LEMONSQUEEZY_LICENSE_KEY": "YOUR-KEY-HERE" }
    }
  }
}

Validation is cached locally for 24 h — fully offline-capable after first run.


License

ShopOps MCP is released under the MIT License. See LICENSE for full terms.


Author: Automatia BCN

Available Tools

12 tools
customers_churnChurn RiskA
Read-onlyIdempotent

Identify customers at risk of churning based on RFM recency + frequency signals. Returns an object with at_risk, hibernating, and lost arrays — each contains customer id, name, email, last_order_date, days_since_last_order, total_spent, total_orders, and a win_back_recommendation string. Use this for targeted re-engagement campaigns.

Inputs: store_id (required).

customers_segmentCustomer SegmentationA
Read-onlyIdempotent

RFM (Recency, Frequency, Monetary) customer segmentation. Categorizes customers into segments: Champions, Loyal, Potential, At Risk, New, Hibernating, Lost — with actionable recommendations.

Inputs: store_id (required).

inventory_forecastInventory ForecastA
Read-onlyIdempotent

Predict stock depletion dates using moving-average sales velocity. Returns reorder points, safety stock levels, and suggested reorder quantities for each product.

Inputs: store_id (required), product_id.

inventory_statusInventory StatusA
Read-onlyIdempotent

Snapshot of current stock levels for a connected store. Returns a summary object with total product count, out-of-stock count, low-stock count (≤10 units), plus two arrays: out_of_stock and low_stock — each containing product id, title, sku, quantity, and status. Items are sorted by urgency (lowest quantity first). Read-only and idempotent.

Inputs: store_id (required).

order_anomaliesOrder Anomaly DetectionA
Read-onlyIdempotent

Statistical anomaly detection on recent orders. Flags high-value orders (>3σ from mean), velocity spikes (customer ordering unusually fast), unusual quantities, off-hours purchases (2am-5am), and new-customer high-value orders. Returns an array of anomalies with order_id, anomaly_type, severity (low/medium/high), reason, and recommended_action. Useful for fraud detection and revenue spike investigation.

Inputs: store_id (required).

pricing_analyzePricing AnalysisA
Read-onlyIdempotent

Analyze pricing across products with margin calculation, sales velocity, and rule-based price optimization suggestions. Returns an array where each element contains product_title, current_price, cost, margin_percent, daily_units_sold, revenue_per_day, suggested_price (or null if no change recommended), and suggestion_reason. Pass product_id to scope to a single product, omit for full catalog.

Inputs: store_id (required), product_id.

pricing_optimizePricing OptimizationA
Read-onlyIdempotent

Filtered pricing recommendations — only products where a price change is suggested. Returns a summary with total_suggestions count and an optimizations array (product, current_price, suggested_price, change_percent, reason, daily_revenue), sorted by absolute change_percent (biggest moves first). Use this instead of pricing_analyze when you only want actionable changes.

Inputs: store_id (required).

product_performanceProduct Performance (ABC Analysis)A
Read-onlyIdempotent

Product performance report with ABC analysis. Category A = top 80% revenue, B = next 15%, C = bottom 5%. Includes trends, margins, and daily sales velocity.

Inputs: store_id (required), period_days.

report_dailyDaily ReportA
Read-onlyIdempotent

Daily operational report: orders, revenue, top products, new vs returning customers, low stock alerts, and anomaly count.

Inputs: store_id (required), date.

report_weeklyWeekly ReportA
Read-onlyIdempotent

Weekly trend report: revenue/order changes vs previous week, customer segment distribution, trending products, and AI-generated insights.

Inputs: store_id (required).

store_connectConnect StoreA

Manage Shopify or WooCommerce store connections. action="connect" adds a new store and performs an initial sync of products, orders, and customers; action="sync" refreshes cached data for an existing store; action="list" returns all connected stores with their sync counts. Returns a JSON payload with store metadata (id, name, platform, url, counts, last_sync) — credentials are never returned.

Inputs: action (required), name, platform, url, +3 more.

store_demo_seedSeed Demo StoreA

Create a realistic demo store populated with 20 products, 40 customers across 6 archetype buckets (champions, loyal, new, at-risk, hibernating, one-off), and 150+ orders spanning the last 6 months. Use this to explore ShopOps without real Shopify or WooCommerce credentials — every tool (inventory_status, customers_segment, order_anomalies, report_weekly, etc.) will return meaningful output on the returned store_id. Safe to call multiple times; each call creates a new demo store with a unique ID. Returns the store_id plus product/customer/order counts.

Inputs: no named parameters.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.3/5.0

    Scored across 12 tools

    Disambiguation5/5

    Each tool targets a distinct aspect of shop operations (customers, inventory, orders, pricing, products, reports, store management). Even similar tools like customers_churn and customers_segment have clear differences in scope and output. There is no overlap that would cause confusion.

    Naming Consistency5/5

    All tool names follow a consistent 'domain_verb' pattern using snake_case (e.g., customers_churn, inventory_forecast, order_anomalies). This makes it easy to infer the tool's purpose and domain from its name.

    Tool Count5/5

    With 12 tools, the server covers all essential aspects of shop operations without being overwhelming. Each tool serves a clear purpose, and the count is appropriate for the server's scope.

    Completeness5/5

    The tool set provides comprehensive coverage for analyzing and managing a shop: customer segmentation and churn, inventory status and forecasting, order anomaly detection, pricing analysis and optimization, product performance, daily/weekly reports, and store connectivity. There are no obvious gaps for the intended use case.

    Maintenance

    ActivityStale
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      B
      quality
      C
      maintenance
      Multi-channel inventory intelligence for Shopify and Amazon sellers. 28 tools for stockout risk, demand forecasts, purchase order management, and sales analytics — with human-in-the-loop safeguards.
      50
      97 npm
      2
      MIT
    • F
      license
      Not graded
      quality
      D
      maintenance
      Hosted MCP server connecting Shopify, Klaviyo, GA4, Meta Ads, Google Ads, Xero, Gorgias and 20+ e-commerce data sources so AI assistants can answer merchant questions that span every source at once.
      -