About Orbis Commerce Mcp
Orbis Commerce Mcp provides MCP access to commerce and retail APIs for product and barcode data. It supports product searches, page parsing, and review summaries, with calls billed in USDC through x402 on Base.
Key features
- 01Validate and decode barcodes
- 02Look up products by UPC
- 03Search Walmart, eBay, and Amazon products
- 04Parse product pages into structured JSON
- 05Summarize Amazon reviews and ratings
Use cases
- 01Identify a product from a barcode or UPC
- 02Compare product listings and prices across retailers
- 03Extract structured details from a product page
- 04Summarize customer feedback into pros and cons
MCP support
The remote MCP server exposes commerce and retail API tools, including product search, barcode lookup, page parsing, and review data. Calls are billed per use in USDC via x402 on Base.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://orbisapi.com/api/mcp/commerceclaude mcp add --transport http commerce https://orbisapi.com/api/mcp/commerce{"mcpServers":{"commerce":{"type":"http","url":"https://orbisapi.com/api/mcp/commerce"}}}Open in Cursor{"servers":{"commerce":{"type":"http","url":"https://orbisapi.com/api/mcp/commerce"}}}Open in VS Code{"mcpServers":{"commerce":{"type":"http","url":"https://orbisapi.com/api/mcp/commerce"}}}{"mcpServers":{"commerce":{"serverUrl":"https://orbisapi.com/api/mcp/commerce"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project READMEOrbis Commerce & Retail MCP 🛒
Real product search, barcode lookup, and retail data APIs for AI agents. Pay per call with USDC on Base — no API keys, no accounts, no subscriptions.
What's Actually In Here
These are the most-called APIs in this domain on Orbis:
| API | Calls | What it does |
|---|---|---|
| Barcode Validator API | 327 | Validate any barcode format and check legitimacy |
| Retail UPC Data | 206 | Look up full product data from a UPC code |
| Walmart Product Search API | 164 | Search Walmart for products with live prices |
| AI Product Description Generator API | 35 | Generate SEO product descriptions from specs |
| eBay Product Search API | 33 | Search eBay listings with prices and availability |
| Ecommerce Product Page Parser API | 32 | Parse any product page into structured JSON |
| Amazon Reviews & Ratings API | 31 | Fetch Amazon reviews and rating breakdowns |
| Barcode Data API | 31 | Detailed product info from barcode/UPC |
| Amazon Product Search API | 29 | Search Amazon products with prices and specs |
| UPC Product Lookup | 18 | Look up product details by UPC code |
| Product Review Summary | 16 | Summarize customer reviews into pros/cons |
| Barcode Validate | 15 | Validate barcode checksums and formats |
| Barcode Decode | 14 | Decode barcode images and strings |
Quick Start
No API key needed. No account. Paste into your MCP client:
Claude Desktop / Claude Code
{
"mcpServers": {
"orbis-commerce": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://orbisapi.com/api/mcp/commerce"]
}
}
}
Config path: ~/Library/Application Support/Claude/claude_desktop_config.json
Cursor / Windsurf / Cline
{
"mcpServers": {
"orbis-commerce": {
"url": "https://orbisapi.com/api/mcp/commerce"
}
}
}
OpenAI Codex CLI
# ~/.codex/config.yaml
mcpServers:
orbis-commerce:
type: url
url: "https://orbisapi.com/api/mcp/commerce"
Example Prompts
Once connected, try:
- "Look up this barcode and tell me what product it is: 012345678905"
- "Search Walmart for protein powder under $40 — show me prices and ratings"
- "Find this product on Amazon and eBay and compare the prices: 'Sony WH-1000XM5'"
- "Parse this product page and give me the specs as JSON: https://..."
- "Summarize the customer reviews for this Amazon product into pros and cons"
- "Validate this UPC code and look up the product: 036000291452"
Direct x402 Usage (Node.js)
import { wrapFetchWithPayment } from "x402-fetch";
import { privateKeyToAccount } from "viem/accounts";
import { createWalletClient, http } from "viem";
import { base } from "viem/chains";
const account = privateKeyToAccount(process.env.WALLET_PRIVATE_KEY);
const walletClient = createWalletClient({ account, chain: base, transport: http() });
const fetch = wrapFetchWithPayment(globalThis.fetch, walletClient);
// Walmart product search — 164 real calls on Orbis
const resp = await fetch(
"https://orbisapi.com/api/proxy/walmart-product-search-api-87729d/search",
{ method: "POST", headers: { "Content-Type": "application/json" },
body: JSON.stringify({ query: "running shoes", limit: 5 }) }
);
console.log(await resp.json());
See example.mjs for a full working script.
All Orbis Domain MCPs
| Domain | URL |
|---|---|
| ₿ Crypto & Blockchain | https://orbisapi.com/api/mcp/crypto |
| 🔍 Research & Data | https://orbisapi.com/api/mcp/research |
| 🛒 Commerce & Retail | https://orbisapi.com/api/mcp/commerce |
| ✈️ Travel | https://orbisapi.com/api/mcp/travel |
| 🌐 All 20,000+ APIs | https://orbisapi.com/api/mcp |
Built by Orbis — the API marketplace for AI agents.
Connect
Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"orbis-commerce": { "url": "https://orbisapi.com/api/mcp/commerce" }
}
}
OpenAI Agents SDK
Python:
from agents.mcp import MCPServerStreamableHttp
from agents import Agent, Runner
mcp = MCPServerStreamableHttp(url="https://orbisapi.com/api/mcp/commerce")
agent = Agent(
name="Orbis Commerce Agent",
model="gpt-4o",
mcp_servers=[mcp]
)
result = await Runner.run(agent, "Browse available commerce APIs")
print(result.final_output)
TypeScript:
import { Agent, run } from "@openai/agents";
import { MCPServerStreamableHttp } from "@openai/agents/mcp";
const mcp = new MCPServerStreamableHttp({
url: "https://orbisapi.com/api/mcp/commerce",
});
const agent = new Agent({
name: "Orbis Commerce Agent",
model: "gpt-4o",
mcpServers: [mcp],
});
const result = await run(agent, "Browse available commerce APIs");
console.log(result.finalOutput);
Calls are billed per-use in USDC via x402 on Base mainnet. No subscription, no API key required.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.
