retail-inventory-mcp-server
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., "@retail-inventory-mcp-serverWhat are the current inventory levels at Fernwood Riverside?"
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.
Retail Inventory API — Server
Implements retail-inventory-api.json (the OpenAPI spec one level up) two
ways from one process: as the literal REST API the spec describes, and as
an MCP server exposing the same 8 operations as tools. Both are backed by
the same in-memory synthetic dataset, since the spec's servers entry
(api.retailpartner.com) is a design placeholder, not a real backend.
No persistence, logging, analytics, or caching — everything lives in
module-level Python lists for the life of the process. Rate-limit response
headers (X-RateLimit-Limit, X-RateLimit-Remaining) are present because
the spec requires them, but are fixed example values, not an enforced
limit — real enforcement would need exactly the kind of stateful
infrastructure this server is deliberately kept free of.
Auth matches the spec's stated model exactly: a Bearer API Key resolves to
one Partner, whose Store/Region/Brand scope filters every query. Demo keys
(see retail_inventory_auth.py):
API Key | Partner | Scope |
| Priya Nair, Store Manager | Fernwood Riverside only |
| Carlos Mendez, Regional VP | Columbus, OH region |
| Alice Smith, Inventory Planner | All Fernwood stores |
Run locally
pip install -r requirements.txt
python retail_inventory_mcp_server.pyServes on http://127.0.0.1:8090 (or $PORT if set):
REST API — the 8 paths exactly as declared in
retail-inventory-api.json(/stores,/stores/{storeId}/inventory-levels,/inventory-levels,/promotional-events,/sales-transactions,/inventory-recommendations,/inventory-recommendations/{recommendationId}/overrides,/metrics/full-price-sell-through-rate) — no/apior version prefix, since none is in the spec.MCP — streamable-HTTP at
/mcp, unchanged from before.Docs —
/serves a Swagger UI page (backed by/openapi.json) for browsing the spec. Not part ofretail-inventory-api.jsonitself, added so the deployed service has something to show a human visiting the root URL instead of a bare 404.
Related MCP server: lightspeed-x
Call the REST API
curl -H "Authorization: Bearer rip_demo_store_key" http://127.0.0.1:8090/storesErrors follow the spec's RFC 9457 Problem Details format
(application/problem+json) for 400/401/404, exactly as documented.
Connect an MCP client
Send Authorization: Bearer <one of the demo keys above> when connecting to
http://127.0.0.1:8090/mcp.
This server cannot be deployed
Maintenance
Related MCP Connectors
Governed data discovery, exact queries, decisions, simulations, and runtime utilities over MCP.
Let AI agents query data and act across all your business apps via MCP.
Agentic commerce with 58 MCP tools for product search, checkout, A2A negotiation, C-Suite analytics.
Multi-tenant MCP gateway for AI commerce. One connection, every store.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables querying ecommerce data (customers, products, orders, reviews) using natural language via Cortex Analyst and Cortex Search, with SQL execution capability, all exposed as MCP tools.-
- AlicenseAqualityAmaintenanceEnables read-only access to Lightspeed X retail data (sales, inventory, products, customers) with aggregated reporting on revenue, COGS, profit, and other metrics for MCP clients like Claude.1MIT
- AlicenseAqualityCmaintenanceEnables an LLM agent to query a Shopify store's catalogue and stock via MCP, with tools for product search, product details, per-location inventory, and low-stock reports.4MIT
- FlicenseAqualityCmaintenanceEnables AI agents to query tenants, browse catalogue items with pricing, pull recent orders, and add products through the MCP tool-calling interface.4-