products-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., "@products-mcp-server recommend products similar to id 5"
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.
products-mcp-server
A custom Model Context Protocol (MCP) server exposing 27 product tools backed by fakestoreapi.com.
It runs three ways from the same code:
Local (stdio) — for Cursor / Claude Desktop, via
src/index.ts→dist/index.js.Render (persistent HTTP) — a long-running Streamable HTTP server, via
src/http.ts→dist/http.js.Vercel (serverless HTTP) — a stateless Streamable HTTP function, via
api/mcp.ts.
Architecture
src/
products-api.ts # Fake Store API client (endpoints + 60s TTL cache)
tools.ts # registerTools(server): all 27 tools (shared)
server.ts # createServer(): builds a configured server (shared)
index.ts # stdio entry point (local)
http.ts # persistent HTTP entry point (Render) — listens on $PORT
api/
mcp.ts # Vercel serverless entry point (stateless Streamable HTTP)
render.yaml # Render blueprint (web service)
vercel.json # Vercel function configAll entry points call createServer(), so the tool set stays identical across transports.
Related MCP server: fake-store-mcp
Tools
# | Tool | Description |
1 |
| All products (optional |
2 |
| One product by |
3 |
| List of categories. |
4 |
| Products in a |
5 |
| Keyword search over title + description. |
6 |
| Products within |
7 |
| Products costing more than |
8 |
| Products costing less than |
9 |
| Single cheapest product. |
10 |
| Single most expensive product. |
11 |
| Sorted by rating (optional |
12 |
| Sorted by review count (optional |
13 |
| Products with rating >= |
14 |
| count / min / max / average / median / total. |
15 |
| Per-category price stats. |
16 |
| Total count (optional |
17 |
| Lightweight id + title list. |
18 |
| A random product. |
19 |
| Compare 2–10 products by |
20 |
| Same-category picks for an |
21 |
| Price after |
22 |
| High-level catalog summary. |
23 |
| Cheapest within a |
24 |
| Highest-rated within a |
25 |
| Create a product (simulated by the API). |
26 |
| Update a product (simulated). |
27 |
| Delete a product (simulated). |
Note: fakestoreapi.com simulates write operations (create/update/delete) and does not persist them.
Local development
npm install
npm run build # tsc: src -> dist
npm run typecheck # type-checks src + api
npm start # runs the stdio serverUse locally in Cursor (~/.cursor/mcp.json)
{
"mcpServers": {
"products": {
"command": "node",
"args": ["c:/Users/serch/OneDrive/Desktop/MCP-Servers/products-mcp-server/dist/index.js"]
}
}
}Re-run npm run build after changing the TypeScript, since Cursor runs the compiled dist/index.js.
To run the HTTP server locally (same one Render uses):
npm run build
npm run start:http # listens on http://localhost:3000/mcp
# health check: curl http://localhost:3000/healthzDeploy to Render
Render runs a persistent Node process (via src/http.ts), which suits MCP well and avoids serverless cold starts / timeouts.
Option A — Blueprint (recommended)
The repo includes render.yaml:
services:
- type: web
name: products-mcp-server
runtime: node
plan: free
buildCommand: npm install && npm run build
startCommand: npm run start:http
healthCheckPath: /healthzPush this folder to a Git repo.
In Render: New → Blueprint, select the repo. Render reads
render.yamland creates the web service.Deploy. Your endpoint will be:
https://<your-service>.onrender.com/mcpOption B — Manual web service
New → Web Service → connect the repo, then set:
Runtime: Node
Build Command:
npm install && npm run buildStart Command:
npm run start:httpHealth Check Path:
/healthz
Connect a client to the Render server
{
"mcpServers": {
"products": { "url": "https://<your-service>.onrender.com/mcp" }
}
}For stdio-only clients, bridge with mcp-remote:
{
"mcpServers": {
"products": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://<your-service>.onrender.com/mcp"]
}
}
}Notes
The server binds to
process.env.PORT(Render sets this automatically). The MCP path defaults to/mcpand can be overridden with theMCP_PATHenv var.Render's free web services sleep after inactivity; the first request after idle may be slow to wake.
The deployed URL is public — add authentication before exposing sensitive tools.
Deploy to Vercel
The api/mcp.ts function serves the MCP server over Streamable HTTP in stateless mode (a fresh server per request — no Redis required).
Push this folder to a Git repo and import it in Vercel (or run
npx vercel).Vercel compiles
api/mcp.tsautomatically; no build step is required for the function.After deploy, your endpoint is:
https://<your-project>.vercel.app/api/mcpConnect a client to the deployed server
If the client supports Streamable HTTP (e.g. recent Cursor):
{
"mcpServers": {
"products": { "url": "https://<your-project>.vercel.app/api/mcp" }
}
}For stdio-only clients, bridge with mcp-remote:
{
"mcpServers": {
"products": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://<your-project>.vercel.app/api/mcp"]
}
}
}Notes & limits
Stateless: each request is self-contained. If you later need SSE streaming / persistent sessions across instances, add Upstash Redis and enable Vercel Fluid Compute.
Timeout:
vercel.jsonsetsmaxDuration: 60; each tool also has a 10s upstream-fetch abort guard.Auth: the deployed URL is public. Add authentication before exposing sensitive tools.
Available Tools
27 toolscompareProductsCompare ProductsB
Compares two or more products side by side by their ids.
Inputs: ids (required).
countProductsCount ProductsB
Counts products, optionally filtered by category.
Inputs: category.
createProductCreate ProductC
Creates a product. Note: fakestoreapi.com simulates writes and does not persist them.
Inputs: image (required), price (required), title (required), category (required), +1 more.
deleteProductDelete ProductA
Deletes a product by id. Note: fakestoreapi.com simulates writes and does not persist them.
Inputs: id (required).
getCategoriesGet CategoriesB
Returns the list of available product categories.
Inputs: no named parameters.
getCategoryStatsGet Category StatsA
Returns per-category product count and average/min/max price.
Inputs: no named parameters.
getCheapestInCategoryGet Cheapest In CategoryB
Returns the cheapest product within a given category.
Inputs: category (required).
getCheapestProductGet Cheapest ProductB
Returns the single cheapest product in the catalog.
Inputs: no named parameters.
getDiscountedPriceGet Discounted PriceB
Calculates a product's price after applying a discount percentage (0-100).
Inputs: id (required), discountPercent (required).
getHighestRatedInCategoryGet Highest Rated In CategoryB
Returns the highest-rated product within a given category.
Inputs: category (required).
getMostExpensiveProductGet Most Expensive ProductA
Returns the single most expensive product in the catalog.
Inputs: no named parameters.
getMostReviewedProductsGet Most Reviewed ProductsB
Returns products sorted by number of ratings (highest first).
Inputs: limit.
getPriceStatsGet Price StatsA
Returns count, min, max, average, median, and total price across all products.
Inputs: no named parameters.
getProductByIdGet Product By IdB
Fetches a single product by its numeric id.
Inputs: id (required).
getProductRecommendationsGet Product RecommendationsC
Recommends products in the same category as the given product id.
Inputs: id (required), limit.
getProductsGet ProductsC
Fetches the product catalog from fakestoreapi.com. Optionally limit and sort by id.
Inputs: sort, limit.
getProductsAbovePriceGet Products Above PriceA
Returns products that cost strictly more than the given price.
Inputs: price (required).
getProductsBelowPriceGet Products Below PriceA
Returns products that cost strictly less than the given price.
Inputs: price (required).
getProductsByCategoryGet Products By CategoryC
Returns products in a category (e.g. 'electronics', 'jewelery', "men's clothing", "women's clothing").
Inputs: category (required), limit.
getProductsByMinRatingGet Products By Minimum RatingC
Returns products with an average rating >= minRating (0-5).
Inputs: minRating (required).
getProductsByPriceRangeGet Products By Price RangeC
Returns products whose price falls within [min, max].
Inputs: max, min.
getRandomProductGet Random ProductA
Returns a single random product from the catalog.
Inputs: no named parameters.
getTopRatedProductsGet Top Rated ProductsC
Returns products sorted by rating (highest first).
Inputs: limit.
listProductTitlesList Product TitlesB
Returns a lightweight list of product ids and titles.
Inputs: no named parameters.
searchProductsSearch ProductsC
Case-insensitive search across product titles and descriptions.
Inputs: query (required), limit.
summarizeCatalogSummarize CatalogA
Returns a high-level summary of the catalog: totals, categories, price range, average rating.
Inputs: no named parameters.
updateProductUpdate ProductC
Updates a product by id. Note: fakestoreapi.com simulates writes and does not persist them.
Inputs: id (required), image, price, title, +2 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 27 tools
Most tools have distinct purposes, but some overlap exists, e.g., getTopRatedProducts vs getMostReviewedProducts vs getProductsByMinRating, and multiple price-filtering tools could cause confusion.
All tool names follow a consistent camelCase verb_noun pattern (e.g., getProductById, createProduct, countProducts), with no mixing of conventions.
27 tools is on the high side; many are specialized queries that could be combined with optional parameters, but each tool serves a clear purpose.
Covers CRUD and a wide range of queries, though lacks a generic sort/filter endpoint and bulk operations; write operations are noted as simulated.
Maintenance
Related MCP Connectors
Product search for AI agents: Amazon + Shopify, cart-to-checkout buy path. Pay-per-call, no API key.
Live data for AI agents. Search the catalog, read the price, call the tool; keys stay server-side.
Backend for AI agents: one batched tool over ~668 actions (hosting, storage, auth, payments).
Clean product data from any URL. Schema.org + AI extraction. 200 free calls/month.
Related MCP Servers
- AlicenseAqualityDmaintenanceProvides seamless access to the Fake Store API for AI assistants with 18 CRUD tools for managing e-commerce data including products, carts, and users. Perfect for e-commerce demos, testing, and learning MCP development with zero configuration required.185 npmMIT
- AlicenseAqualityDmaintenanceProvides AI assistants with access to the Fake Store API for e-commerce prototyping and testing, enabling queries on products, carts, and users.912 npmMIT
- AlicenseNot gradedqualityDmaintenanceProvides tools for image generation, weather, geocoding, and basic utilities, deployable on Vercel via Streamable HTTP.ISC
- AlicenseBqualityCmaintenanceEnables AI clients to perform full CRUD operations on e-commerce products stored in MySQL, including search with pagination, AI-powered description generation via sampling, and low-stock inventory monitoring. It also exposes product catalog resources and pre-built prompt templates over both stdio and HTTP/SSE transports.47 npmMIT